GPT-5 (opens in new tab)

It is frequently suggested that once one of the AI companies reaches an AGI threshold, they will take off ahead of the rest. It's interesting to note that at least so far, the trend has been the opposite: as time goes on and the models get better, the performance of the different company's gets clustered closer together. Right now GPT-5, Claude Opus, Grok 4, Gemini 2.5 Pro all seem quite good across the board (ie they can all basically solve moderately challenging math and coding problems).

As a user, it feels like the race has never been as close as it is now. Perhaps dumb to extrapolate, but it makes me lean more skeptical about the hard take-off / winner-take-all mental model that has been pushed.

Would be curious to hear the take of a researcher at one of these firms - do you expect the AI offerings across competitors to become more competitive and clustered over the next few years, or less so?

GPT-5 knowledge cutoff: Sep 30, 2024 (10 months before release).

Compare that to

Gemini 2.5 Pro knowledge cutoff: Jan 2025 (3 months before release)

Claude Opus 4.1: knowledge cutoff: Mar 2025 (4 months before release)

https://platform.openai.com/docs/models/compare

https://deepmind.google/models/gemini/pro/

https://docs.anthropic.com/en/docs/about-claude/models/overv...

Going by the system card at: https://openai.com/index/gpt-5-system-card/

> GPT‑5 is a unified system . . .

OK

> . . . with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say “think hard about this” in the prompt).

So that's not really a unified system then, it's just supposed to appear as if it is.

This looks like they're not training the single big model but instead have gone off to develop special sub models and attempt to gloss over them with yet another model. That's what you resort to only when doing the end-to-end training has become too expensive for you.

I'm not really convinced, the benchmark blunder was really strange but the demos were quite underwhelming, and it appears this was reflected by a huge market correction in the betting markets as to who will have the best AI by end of the year.

What excites me now is that Gemini 3.0 or some answer from Google is coming soon and that will be the one I will actually end up using. It seems like the last mover in the LLM race is more advantageous.

The marketing copy and the current livestream appear tautological: "it's better because it's better."

Not much explanation yet why GPT-5 warrants a major version bump. As usual, the model (and potentially OpenAI as a whole) will depend on output vibe checks.

Watching the livestream now, the improvement over their current models on the benchmarks is very small. I know they seemed to be trying to temper our expectations leading up to this, but this is much less improvement than I was expecting

What's going on with this plot's y-axis?

https://bsky.app/profile/tylermw.com/post/3lvtac5hues2n

Some people have hypothesized that GPT-5 is actually about cost reduction and internal optimization for OpenAI, since there doesn't seem to be much of a leap forward, but another element that they seem to have focused on that'll probably make a huge difference to "normal" (non-tech) users is making precise and specifically worded prompts less necessary.

They've mentioned improvements in that aspects a few times now, and if it actually materializes, that would be a big leap forward for most users even if underneath GPT-4 was also technically able to do the same things if prompted just the right way.

Ok this[0] sounds very, uh bold to me? Surely this is going to break a ton of workflows etc seemingly with nearly no notice? I'm assuming 'launches' equates with 'fully rolls out' or something but it's not that clear to me.

    When GPT-5 launches, several older models will be retired, including:
        - GPT-4o
        - GPT-4.1
        - GPT-4.5
        - GPT-4.1-mini
        - o4-mini
        - o4-mini-high
        - o3
        - o3-pro

     If you open a conversation that used one of these models, ChatGPT will automatically switch it to the closest GPT-5 equivalent. Chats with 4o, 4.1, 4.5, 4.1-mini, o4-mini, or o4-mini-high will open in GPT-5, chats with o3 will open in GPT-5-Thinking, and chats with o3-Pro will open in GPT-5-Pro (available only on Pro and Team).

[0] https://help.openai.com/en/articles/11909943-gpt-5-in-chatgp...

> 400,000 context window

> 128,000 max output tokens

> Input $1.25

> Output $10.00

Source: https://platform.openai.com/docs/models/gpt-5

If this performs well in independent needle-in-haystack and adherence evaluations, this pricing with this context window alone would make GPT-5 extremely competitive with Gemini 2.5 Pro and Claude Opus 4.1, even if the output isn't a significant improvement over o3. If the output quality ends up on-par or better than the two major competitors, that'd be truly a massive leap forward for OpenAI, mini and nano maybe even more so.

ChatGPT5 in this demo:

> For an airplane wing (airfoil), the top surface is curved and the bottom is flatter. When the wing moves forward:

> * Air over the top has to travel farther in the same amount of time -> it moves faster -> pressure on the top decreases.

> * Air underneath moves slower -> pressure underneath is higher

> * The presure difference creates an upward force - lift

Isn't that explanation of why wings work completely wrong? There's nothing that forces the air to cover the top distance in the same time that it covers the bottom distance, and in fact it doesn't. https://www.cam.ac.uk/research/news/how-wings-really-work

Very strange to use a mistake as your first demo, especially while talking about how it's phd level.

They will retire lots of models: GPT-4o, GPT-4.1, GPT-4.5, GPT-4.1-mini, o4-mini, o4-mini-high, o3, o3-pro.

https://help.openai.com/en/articles/6825453-chatgpt-release-...

"If you open a conversation that used one of these models, ChatGPT will automatically switch it to the closest GPT-5 equivalent."

- 4o, 4.1, 4.5, 4.1-mini, o4-mini, or o4-mini-high => GPT-5

- o3 => GPT-5-Thinking

- o3-Pro => GPT-5-Pro

That SWE-bench chart with the mismatched bars (52.8% somehow appearing larger than 69.1%) was emblematic of the entire presentation - rushed and underwhelming. It's the kind of error that would get flagged in any internal review, yet here it is in a billion-dollar product launch. Combined with the Bernoulli effect demo confidently explaining how airplane wings work incorrectly (the equal transit time fallacy that NASA explicitly debunks), it doesn't inspire confidence in either the model's capabilities or OpenAI's quality control.

The actual benchmark improvements are marginal at best - we're talking single-digit percentage gains over o3 on most metrics, which hardly justifies a major version bump. What we're seeing looks more like the plateau of an S-curve than a breakthrough. The pricing is competitive ($1.25/1M input tokens vs Claude's $15), but that's about optimization and economics, not the fundamental leap forward that "GPT-5" implies. Even their "unified system" turns out to be multiple models with a router, essentially admitting that the end-to-end training approach has hit diminishing returns.

The irony is that while OpenAI maintains their secretive culture (remember when they claimed o1 used tree search instead of RL?), their competitors are catching up or surpassing them. Claude has been consistently better for coding tasks, Gemini 2.5 Pro has more recent training data, and everyone seems to be converging on similar performance levels. This launch feels less like a victory lap and more like OpenAI trying to maintain relevance while the rest of the field has caught up. Looking forward to seeing what Gemini 3.0 brings to the table.

For day to day coding, I've found Anthropic to be killing it with Sonnet 3.7 and now Sonnet 4, and Claude Code feeling like it has even bigger advantages over when it's used in Cursor (And I can't explain why).

I don't even try to use the OpenAI models because it's felt like night and day.

Hopefully GPT-5 helps them catch up. Although I'm sure there are 100 people that have their own personal "hopefully GPT-5 fixes my personal issue with GPT4"

I am thoroughly unimpressed by GPT-5. It still can't compose iambic trimeters in ancient Greek with a proper penthemimeral cæsura, and it insists on providing totally incorrect scansion of the flawed lines it does compose. I corrected its metrical sins twice, which sent it into "thinking" mode until it finally returned a "Reasoning failed" error.

There is no intelligence here: it's still just giving plausible output. That's why it can't metrically scan its own lines or put a cæsura in the right place.

Pricing seems good, but the open question is still on tool calling reliability.

Input: $1.25 / 1M tokens Cached: $0.125 / 1M tokens Output: $10 / 1M tokens

With 74.9% on SWE-bench, this inches out Claude Opus 4.1 at 74.5%, but at a much cheaper cost.

For context, Claude Opus 4.1 is $15 / 1M input tokens and $75 / 1M output tokens.

> "GPT-5 will scaffold the app, write files, install dependencies as needed, and show a live preview. This is the go-to solution for developers who want to bootstrap apps or add features quickly." [0]

Since Claude Code launched, OpenAI has been behind. Maybe the RL on tool calling is good enough to be competitive now?

[0]https://github.com/openai/gpt-5-coding-examples

‘Twas the night before GPT-5, when all through the social-media-sphere, Not a creature was posting, not even @paulg nor @eshear

Next morning’s posts were prepped and scheduled with care, In hopes that AGI soon would appear …

What's going on with their SWE bench graph?[0]

GPT-5 non-thinking is labeled 52.8% accuracy, but o3 is shown as a much shorter bar, yet it's labeled 69.1%. And 4o is an identical bar to o3, but it's labeled 30.8%...

[0] https://i.postimg.cc/DzkZZLry/y-axis.png

Wait, isn't the Bernoulli effect thing they're demoing now wrong? I thought that was a "common misconception" and wings don't really work by the "longer path" that air takes over the top, and that it was more about angle of attack (which is why planes can fly upside down).

It seems like it's actually an ideal "trick" question for an LLM actually, since so much content has been written about it incorrectly. I thought at first they were going to demo this to show that it knew better, but it seems like it's just regurgitating the same misleading stuff. So, not a good look.

They really nerfed Plus[0]. 80 messages every 3 hours for normal GPT-5. And only 200 messages per week for GPT-5 Thinking. It seems like terrible value.

Before it was: 100 o3 per week 100 o4-mini-high per day 300 o4-mini per day 50 4.5 per week

[0] https://help.openai.com/en/articles/11909943-gpt-5-in-chatgp...

Anecdotally, as someone who operates in a very large legacy codebase, I am very impressed by GPT-5's agentic abilities so far. I've given it the same tasks I've given Claude and previous iterations via the Codex CLI, and instead of getting loss due to the massive scope of the problem, it correctly identifies the large scope and breaks it down into it's correct parts and creates the correct plan and begins executing.

I am wildly impressed. I do not believe that the 0.x% increase in benchmarks tell the story of this release at all.

Something that's really hitting me is something brought up in this piece:

https://www.interconnects.ai/p/gpt-5-and-bending-the-arc-of-...

When a model comes out, I usually think about it in terms of my own use. This is largely agentic tooling, and I mostly us Claude Code. All the hallucination and eval talk doesn't really catch me because I feel like I'm getting value of these tools today.

However, this model is not _for_ me in the same way models normally are. This is for the 800m or whatever people that open up chatgpt every day and type stuff in. All of them have been stuck on GPT-4o unbeknwst to them. They had no idea SOTA was far beyond that. They probably dont even know that there is a "model" at all. But for all these people, they just got a MAJOR upgrade. It will probably feel like turning the lights on for these people, who have been using a subpar model for the past year.

That said I'm also giving GPT-5 a run in Codex and it's doing a pretty good job!

The eval bar I want to see here is simple: over a complex objective (e.g., deploy to prod using a git workflow), how many tasks can GPT-5 stay on track with before it falls off the train. Context is king and it's the most obvious and glaring problem with current models.

It's a really good model from my testing so far. You can see the difference in how it tries to use tools to the greatest extent when answering a question, especially compared to 4.1 and o3. In this example it used 6! tool calls in the first response to try and collect as much info as possible.

https://promptslice.com/share/b-2ap_rfjeJgIQsG

The silent victory here is this seems like it is being built to be faster and cheaper than o3 while presenting a reasonable jump, which is an important jump in scaling law

On the other hand if it's just getting bigger and slower it's not a good sign for LLMs

Does this mean AGI is cancelled? 2027 hard takeoff was just sci-fi?

74.9 SWEBench. This increases the SOTA by a whole .4%. Although the pricing is great, it doesn't seem like OpenAI found a giant breakthrough yet like o1 or Claude 3.5 Sonnet

# GPT5 all official links

Livestream link: https://www.youtube.com/live/0Uu_VJeVVfo

Research blog post: https://openai.com/index/introducing-gpt-5/

Developer blog post: https://openai.com/index/introducing-gpt-5-for-developers

API Docs: https://platform.openai.com/docs/guides/latest-model

Note the free form function calling documentation: https://platform.openai.com/docs/guides/function-calling#con...

GPT5 prompting guide: https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_g...

GPT5 new params and tools: https://cookbook.openai.com/examples/gpt-5/gpt-5_new_params_...

GPT5 frontend cookbook: https://cookbook.openai.com/examples/gpt-5/gpt-5_frontend

prompt migrator/optimizor https://platform.openai.com/chat/edit?optimize=true

Enterprise blog post: https://openai.com/index/gpt-5-new-era-of-work

System Card: https://openai.com/index/gpt-5-system-card/

What would you say if you could talk to a future OpenAI model? https://progress.openai.com/

coding examples: https://github.com/openai/gpt-5-coding-examples

Note it's not available to everyone yet:

> GPT-5 Rollout

> We are gradually rolling out GPT-5 to ensure stability during launch. Some users may not yet see GPT-5 in their account as we increase availability in stages.

Wish they would stop mentioning AGI. It's like the creator of a new car claiming it's a step closer to teleportation.

Is anyone else having problems with factual correctness? I had a number of 4o and o3 conversations going and those models were factually correct about a number of different subjects.

Asking GPT-5 about the same things results in wrong answers even though its training data is newer. And it won't look things up to correct itself unless I manually switch to the thinking variant.

This is worse. I cancelled my subscription.

SWE-Bench Verified score, with thinking, ties Opus 4.1 without thinking.

AIME scores do not appear too impressive at first glance.

They are downplaying benchmarks heavily in the live stream. This was the lab that has been flexing benchmarks as headline figures since forever.

This is a product-focused update. There is no significant jump in raw intelligence or agentic behavior against SOTA.

These presenters all give off such a “sterile” vibe

Seems LLMs really hit the wall.

Very funny. The very first answer it gave to illustrate its "Expert knowledge" is quite common, and it's wrong. What's even funnier is that you can find why on Wikipedia: https://en.wikipedia.org/wiki/Lift_(force)#False_explanation... What's terminally funny is that in the visualisation app, it used a symmetric wing, which of course wouldn't generate lift according to its own explanation (as the travelled distance and hence air flow speed would be the same). I work as a game physics programmer, so I noticed that immediately and almost laughed. I watched only that part so far while I was still at the office, though.

Sam Altman, in the summer update video:

> "[GPT-5] can write an entire computer program from scratch, to help you with whatever you'd like. And we think this idea of software on demand is going to be one of the defining characteristics of the GPT-5 era."

GPT-5 set a new record on my Confabulations on Provided Texts benchmark: https://github.com/lechmazur/confabulations/

LLMs hitting a wall would be incredible. We could actually start building on the tech we have.

Answer in one word: Underwhelming.

Bad data on graphs, demos that would have been impressive a year ago, vibe coding the easiest requests (financial dashboard), running out of talking points while cursor is looping on a bug, marginal benchmark improvements. At least the models are kind of cheaper to run.

Did they just say they're deprecating all of OpenAI's non-GPT-5 models?

I know HN isn’t the place to go for positive, uplifting commentary or optimism about technology - but I am truly excited for this release and grateful to all the team members who made it possible. What a great time to be alive.

It's very interesting how memetic the language around different models is. Elon seems to have coined "PhD level intelligence in all topics" and now Sam repeated it in his presentation. Despite it not having an actual meaning. I think OpenAI will coin they've achieved AGI first (as they have incentives to based on the rumored contract with MSFT), and then everyone will claim we've achieved it.

It's very unclear if OpenAI has been casually leaking things to create buzz, but a few days ago there was a pretty stunning pelican on a bike attempt: https://old.reddit.com/r/OpenAI/comments/1mettre/gpt5_is_alr...

In practice, it's very clear to me that the most important value in writing software with an LLM isn't it's ability to one-shot hard problems, but rather it's ability to effectively manage complex context. There are no good evals for this kind of problem, but that's what I'm keenly interested in understanding. Show me GPT-5 can move through 10 steps in a list of tasks without completely losing the objective by the end.

The reduction in hallucinations seems like potentially the biggest upgrade. If it reduces hallucinations by 75% or more over o3 and GPT-4o as the graphs claim, it will be a giant step forward. The inability to trust answers given by AI is the biggest single hurdle to clear for many applications.

Already a lot of comments here (2188 at the time of this comment) but wanted to share my 2c:

* It feels a bit more competent, as if it had more nuance or detail to say about each point.

* It got a few obscure details about OpenBSD correct right away - both Sonnet 4 and 4o sometimes conflate Linux and OpenBSD commands.

* It was fun asking GPT-5 to not only answer the query, but also to provide a brief analysis of the query itself for insights into myself!

Not a detailed review, but just a couple things I noticed with some limited usage.

The presentation asks for a moving svg to illustrate Bernoulli, that's suspiciously close to a Pelican.

Whenever OpenAI releases a new ChatGPT feature or model, it's always a crapshoot when you'll actually be able to use it. The headlines - both from tech media coverage and OpenAI itself - always read "now available", but then I go to ChatGPT (and I'm a paid pro user) and it's not available yet. As an engineer I understand rollouts, but maybe don't say it's generally available when it's not?

I ran the below prompt to both Kimi2 and GPT5.

how many rs in cranberry?

-- GPT5's response: The word cranberry has two “r”s. One in cran and one in berry.

Kimi2's response: There are three letter rs in the word "cranberry".

created a summary of comments from this thread about 15 hours after it had been posted and had 1983 comments, using gpt-5-high and gemini-2.5-pro using a prompt similar to simonw [1]. Used a Python script [2] that I wrote to generate the summary.

- gpt-5-high summary: https://gist.github.com/primaprashant/1775eb97537362b049d643...

- gemini-2.5-pro summary: https://gist.github.com/primaprashant/4d22df9735a1541263c671...

[1]: https://news.ycombinator.com/item?id=43477622

[2]: https://gist.github.com/primaprashant/f181ed685ae563fd06c49d...

Nay, laddie, that's no' the real AGI Scotsman. He's grander still! Wait til GPT-6 come out, you'll be blown away!

https://idiallo.com/byte-size/ai-scotsman

Disclaimer -> We are not a doctor or health advice, marketing -> More useful health answers

I didn't know that OpenAI added what they call organization verification process for API calls for some models. While I haven't noticed this change at work using OpenAI models, when I wanted to try GPT-5 on my personal laptop, I came across this obnoxious verification issue.

It seems that it's all because that users can get thinking traces from API calls, and OpenAI wants to prevent other companies from distilling their models.

Although I don't think OpenAI will be threatened by a single user from Korea, I don't want to go through this process for many reasons. But who knows that this kind of verification process may become norm and users will have no ways to use frontier models. "If you want to use the most advanced AI models, verify yourself so that we can track you down when something bad happens". Is it what they are saying?

It seems to me that there’s no way to achieve AGI with the current LLM approach. New releases have small improvements, live we’re hitting some kind of plateau. And I say this a a heavy LLM user. Don’t fire your employees just yet.

OpenAI taking a page out of Apple's book and only comparing against themselves

Is it bad that I hope it's not a significant improvement in coding?

> With GPT-5 we will be deprecating all of our prior models

Wow, they actually did it

Every release of every SOTA model is the same.

"It's like having a bunch of experts at your fingertips"

"Our most capable model ever"

"Complex reasoning and chain of thought"

Short anything that’s riding on AGI coming soon. This presentation has gotten rid of all my fears of my children growing up in a crazy winner take all AGI world.

For web app generation, gpt-5 seems to route my prompt to the reasoning model. Interestingly, gpt-4.1 often produced more creative or aesthetically interesting designs. In some cases, a bit of controlled hallucination (via temperature) is actually desirable, especially when generating UI ideas. Anyone else seeing this tradeoff?

I could well be missing something obvious but it seems like the jump between 4 & 5 is much less than many will be anticipating

GPT-5 was supposed to make choosing models and reasoning efforts simpler. I think they made it more complex.

> GPT‑5’s reasoning_effort parameter can now take a minimal value to get answers back faster, without extensive reasoning first.

> While GPT‑5 in ChatGPT is a system of reasoning, non-reasoning, and router models, GPT‑5 in the API platform is the reasoning model that powers maximum performance in ChatGPT. Notably, GPT‑5 with minimal reasoning is a different model than the non-reasoning model in ChatGPT, and is better tuned for developers. The non-reasoning model used in ChatGPT is available as gpt-5-chat-latest.

In terms of raw prose quality, I'm not convinced GPT-5 sounds "less like AI" or "more like a friend". Just count the number of em-dashes. It's become something of a LLM shibboleth.

Hmm, deprecating all previous models because GPT-5 is launched feels like a big move. I wonder how the schedule for the deprecation will look like.

I asked it to count letters in his answer. First it asked me what answer, then suggested Python code that will count letter in gpt api reply, then gave wrong answer, then dropped my connection. Wonderfull product. AGI is so near, you u can almost smell it...

Is GPT-5 using a new pretrained base, or is it the same as GPT-4.1?

Given the low cost of GPT-5, compared to the prices we saw with GPT-4.5, my hunch is that this new model is actually just a bunch of RL on top of their existing models + automatic switching between reasoning/non-reasoning.

Anyone have an explanation for openai announcing their newest bestest replace all the others AI with slides of such embarrassing incompetence that most of this discussion is mocking them?

I've got nothing. Cannot see how it helps openai to look incompetent while trying to raise money.

The model "gpt-5" is not available. The link you opened specified a model that isn't available for your org. We're using the default model instead.

Tech aside (covered well by other commenters), the presentation itself was incredibly dry. Such a stark difference in presenting style here compared to, for example, Apple's or Google's keynotes. They should really put more effort into it.

My 2 cents

There would be no GPT without Google, no Google without the WWW, no WWW without TCP/IP. This is why I believe calling it "AI" is a mistake or just for marketing, we should call all of them GPTs or search engines 2.0. This is the natural next step after you have indexed most of the web and collected most of the data.

Also there would be no coding agents without Free Software and Open-Source.

So this was supposed to be agi. Jikes.

I know that the number is mostly marketing, but are they forced to call it 5 because of external pressure. This seems more like a GPT 4.x

Wow, what a breakthrough! A couple of % of benchmark improvements at a couple of % decrease of price per token!

With a couple of more trillions from investors in his company, Sama can really keep launching successful, groundbreaking and innovative products like:

- Study Mode (a pre-prompt that you can craft yourself): https://openai.com/index/chatgpt-study-mode/

- Office Suite (because nothing screams AGI like an office suite: https://www.computerworld.com/article/4021949/openai-goes-fo...)

- ChatGPT5 (ChatGPT4 with tweaks) https://openai.com/gpt-5/

I can almost smell the singularity behind the corner, just a couple of trillion more! Please investors!

Anecdotal review:

Been using it all morning. Had to switch back to 4. 5 has all of the problems that 2/3 had with ignoring any context, flagrantly ignoring the 'spirit' of my requests, and talking to me like I'm a little baby.

Not to mention almost all of my prompts result in a several minute wait with "thinking longer about the answer".

What surprises me the most is that there is no benchmarks table right at the top. Maybe the improvements are not to call home about?

Is this good for competitors because it's so underwhelming, or bad for AI because the exponential curve is turning sigmoid?

Seems like it's just repackaging and UX, not really intelligence updgrade. They know that distribution wins so they want to be most approachable. Maybe multimodal improvements are there.

Not that this proves GPT-5 sucks, but it made me laugh that I could cheese the rolling ball minigame by holding spacebar.

API usage requires organization verification with your ID :(.

So far GPT-5 has not been able to pass my personal "Turing test" which has been unsuccessful for the past several years starting through various versions of Dall-e up to the latest model. I want it to create an image of Santa Claus pulling the sleigh with a reindeer in the sleigh holding the reins, driving the sleigh. No matter how I modify the prompt it is still unable to create this image that my daughter requested a few years ago. This is an image that is easily imagined and drawn by a small child yet the most advanced AI models still can't produce it. I think this is a good example that these models are unable to "imagine" something that falls outside of the realm of it's training data.

Just a week ago I added Qwen3-Coder (the 30b one) to our corporate LLM server, enabled Artifacts in LibreChat, and demoed creating a snake clone in zero shot to coworkers. And now seeing the same exact thing from GPT5's live presentation :) It even has the identical layout.

I have a canonical test for chatbots -- I ask them who I am. I'm sufficiently unknown in modern times that it's a fair test. Just ask, "Who is Paul Lutus?"

ChatGPT 5's reply is mostly made up -- about 80% is pure invention. I'm described as having written books and articles whose titles I don't even recognize, or having accomplished things at odds with what was once called reality.

But things are slowly improving. In past ChatGPT versions I was described as having been dead for a decade.

I'm waiting for the day when, instead of hallucinating, a chatbot will reply, "I have no idea."

I propose a new technical Litmus test -- chatbots should be judged based on what they won't say.

This health segment is completely wild. Seeing Sam fully co-sign the replacement of medical advice with ChatGPT in such a direct manner would have been unheard of two years ago. Waiting for GPT-6 to include a segment on replacing management consultants.

I wish they posted detailed metrics and benchmarks with such a "big" (loud) update.

I've tried it in cursor and I didn't like it. The claude-4-sonnet gives me far better results.

Also it's a lot slower than Claude and Google models.

In general GPT models doesn't work well for me for both coding and general questions.

This was the first product demo I've watched in my entire life. Not because I am excited for the new tech, but because I'm anxious to know if I'm already being put out of my job. Not this time, it seems.

First impressions: the emoji trigger happiness of 4o is totally gone. Bolding still happens.

There appear to be 4 ways to run a query now: a) GPT5, b) GPT5 and toggle "extra thinking" on, c) "GPT5 with thinking", and d) "GPT5 with thinking" then click "quick answer" which aborts thinking (this mode is possibly identical with GPT5)

I don't find this much simpler than 4o, o3, etc. It's just reordering the hierarchies. Now the model name is no longer descriptive at all and one has to add which mode one ran it in.

I did a little test that I like to do with new models: "I have rectangular space of dimensions 30x30x90mm. Would 36x14x60mm battery fit in it, show in drawing proof". GPT5 failed spectacularly.

Since the stream has been on some starting screen for several minutes, I went to check whether there are watch-along streams on Twitch for this - there are a few, and for some reason every one of them is in Spanish. I know Spanish-language streams are a big thing, but it's curious that there's three Spanish GPT-5 watchalong streams (two with 50-ish viewers and one with 2.5k) and none in English.

edit: YouTube has a few English "watch party" streams, although there too, the Spanish ones have many times more viewers.

But can it say “I don’t know” if ya know, it doesn’t

I am very puzzled that I cannot search for the word 'blueberry' in this HN discussion. Is my browser broken, or is the subject inappropriate to raise in this community?

Considering how they hyped it up (eg. “Lol normies go about their day and have no idea whats coming etc”) they have to show some AGI level llm or stop overhyping their 2% improvements.

They vibe coded the update.

"Your organization must be verified to use the model `gpt-5`. Please go to: https://platform.openai.com/settings/organization/general and click on Verify Organization. If you just verified, it can take up to 15 minutes for access to propagate."

And every way I click through this I end in an infinity loop on the site...

Looks like the predictions of 2027 were on point. The developers at OpenAI are now clearly deferring to the judgement of their own models in their development process.

The incremental improvement reminds me of iPhone releases still impressive, but feels like we’re in the ‘refinement era’ of LLMs until another real breakthrough.

I wish the ChatGPT Plus plan had a Claude Code equivalent.

I can sense the scream of a million bubbles popping up. I see it in the tea leaves.

I hate the direction that American AI is going, and the model card of OpenAI is especially bad.

I am a synthetic biologist, and I use AI a lot for my work. And it constantly denies my questions RIGHT NOW. But of course OpenAI and Anthropic have to implement more - from the GPT5 introduction: "robust safety stack with a multilayered defense system for biology"

While that sounds nice and all, in practical terms, they already ban many of my questions. This just means they're going to lobotomize the model more and more for my field because of the so-called "experts". I am an expert. I can easily go read the papers myself. I could create a biological weapon if I wanted to with pretty much zero papers at all, since I have backups of genbank and the like (just like most chemical engineers could create explosives if they wanted to). But they are specifically targeting my field, because they're from OpenAI and they know what is best.

It just sucks that some of the best tools for learning are being lobotomized specifically for my field because of people in AI believe that knowledge should be kept secret. It's extremely antithetical to the hacker spirit that knowledge should be free.

That said, deep research and those features make it very difficult to switch, but I definitely have to try harder now that I see where the wind is blowing.

They claim it thinks the "perfect amount" but there is no perfect amount. It all depends on willingness to pay, latency tolerance, etc.

Neat, more scalable intelligence for me to tell "plz fix" over my code

Finally got access to it. It's so awful. I asked it something, answered in Spanish with something completely different. In another conversation, it kept giving me completely different answers to something I didn't even ask. Telling it to stop doesn't do anything. It ignores it and continues a conversation with itself.

On the Extended NYT Connections benchmark, GPT-5 Medium Reasoning scores close to o3 Medium Reasoning, and GPT-5 Mini Medium Reasoning scores close to o4-Mini Medium Reasoning: https://github.com/lechmazur/nyt-connections/

A bit unrelated: The "countdown animation", just like Google I/O's, how do people make those? The countdown is probably dynamically generated, as they don't know when the event will actually start? Is there like a JavaScript library, or CapCut template, or something?

Especially Google IO, each year is different, it seems purpose built?

The live stream just has Altman interviewing a lady who was diagnosed 3 different cancers.

GPT4 gave her better response than doctors she said.

So models are getting pretty good at oneshotting many small project ideas I've had. What's a good place to host stuff like that? Like a modern equivalent of Heroku? I used to use a VPS for everything but I'm looking for a managed solution.

I heard replit is good here with full vertical integration, but I haven't tried it in years.

The dev blog makes it sound like they’re aiming more for “AI teammate” than just another upgrade. That said, it’s hard to tell how much of this is real improvement vs better packaging. Benchmarks are cherry-picked as usual, and there’s not much comparison to other models. Curious to hear how it performs in actual workflows.

GPT-5 just dropped for my ChatGPT Plus.

Two concerning things: - thinking/non-thinking is still not really unified, you can chose and the non-thinking version still doesn't start thinking on tasks that could obviously get better results with thinking

- all the older models are gone! No 4o, 4.1, 4.5, o3 available anymore

Absolutely nothing new or groundbreaking. It's just a more tuned version of a basic LLM architecture.

My first impressions: not impressed at all. I tried using this for my daily tasks today and for writing it was very poor. For this task o3 was much better. I'm not planning on using this model in the upcoming days, I'll keep using Gemini 2.5 Pro, Claude Sonnet, and o3.

Very generic, broad and bland presentation. Doesn't seem to have any killer features. No video or audio capabilities shown. The coding seems to be on par with Claude 3.7 at best. No mention of MCP which is about the most important thing in AI right now IMO. Not impressed.

It does make me wonder about human training, aka education. Could it be that ingesting/reading a better quality literature, math, and other topics would necessarily result in a higher intelligence?

Interesting readign the progress.openai.com sample prompts https://progress.openai.com/?prompt=6

I would say GPT-5 reads more scientific and structured, but GPT-4 more human and even useful. For the prompt:

Is uncooked meat actually unsafe to eat? How likely is someone to get food poisoning if the meat isn’t cooked?

GPT-4 makes the assumption you might want to know safe food temperatures, and GPT-5 doesn't. Really hard to say which is "better", but GPT-4 seems more useful to every day folks, but maybe GPT-5 for the scientific community?

Then interesting that on ChatGPT vibe check website "Dan's Mom" is the only one who says it's a game changer.

Not so sure about the behind the scenes "automatic router". What's to stop OpenAI from slowing gimping GPT-5 over time or during times of high demand? It seems ripe for delivering inconsistent results while not changing the price.

MCP support has landed in gpt-5 but the video has no mention at all! https://platform.openai.com/docs/models/gpt-5

Hypothesis: to the average user this will feel like a much greater jump in capability then to the average HNer, because most users were not using the model selector. So it'll be more successful than the benchmarks suggest.

Tried out, I still get 9.11 is larger than 9.9.

> "If you’re on Plus or Team, you can also manually select the GPT-5-Thinking model from the model picker with a usage limit of up to 200 messages per week."

And what's the reasoning effort parameter set to?

This is really sounding like Apple's "We changed everything. Again."

Context-Free Gammar support for custom tools is huge. I'm stoked about this.

Ha. I asked it to write some code for the Raspberry Pi RP2350. It told me there might be some confusion as there is no official product release of the RP2350. If it doesn’t know that, then what else doesn’t it know?

So OpenAI added withpersona mandatory for API access. Thank you and goodbye.

What did Ilya see? (or rather what could he no longer bear to see?)

> Academics distorting graphs to make their benchmarks appear more impressive

> lavish 1.5 million dollar bonuses for everyone at the company

> Releasing an open source model that doesn't even use latent multi head attention in a open source AI world led by Chinese labs

> Constantly overhyping models as scary and dangerous to buy time to lobby against competitors and delay product launches

> Failing to match that hype as AGI is not yet here

For those who haven't seen, a little bit of early stuff:

Official OpenAI gpt-5 coding examples repo: https://github.com/openai/gpt-5-coding-examples (https://news.ycombinator.com/item?id=44826439)

Github leak: https://news.ycombinator.com/item?id=44826439

The upgrade from GPT3.5 to GPT4 was like going from a Razr to an iPhone, just a staggering leap forward. Everything since then has been successive iPhone releases (complete with the big product release announcements and front page HN post). A sequence of largely underwhelming and basically unimpressive incremental releases.

Also, when you step back and look at a few of those incremental improvements together, they're actually pretty significant.

But it's hard not to roll your eyes each time they trot out a list of meaningless benchmarks and promise that "it hallucinates even less than before" again

ugh still fails my test prompt: https://chatgpt.com/share/689507c7-5394-8009-b836-c6281a246e...

"Assume the earth was just an ocean and you could travel by boat to any location. Your goal is to always stay in the sunlight, perpetually. Find the best strategy to keep your max speed as low as possible"

o3 pro gets it right though..

One interesting thing I noticed in these "fixing bugs" demos is that people don't seem to resolve the bugs "traditionally" before showing off the capabilities of this new model.

I would like to see a demo where they go through the bug, explain what are the tricky parts and show how this new model handle these situations.

Every demo I've seen seems just the equivalent of "looks good to me" comment in a merge request.

Every piece of promotional material that OpenAI produces looks like a 20 year old Apple preso accidentally opened on a computer missing the Myriad font.

I need a 2x speed on live video

Seems like we're in the endgame for OpenAI and hence the AI bubble. Nothing mind-blowing, just incremental changes.

They've topped and are looking to cash out:

https://www.reuters.com/business/openai-eyes-500-billion-val...

I asked ChatGPT 5 about the main differences between 4 and 5, and it said:

"I couldn’t find any credible, up-to-date details on a model officially named “GPT-5” or formal comparisons to “GPT-4o.” It’s possible that GPT-5, if it exists, hasn't been announced publicly or covered in verifiable sources … GPT-5 as of August 8, 2025 has no formal release announcement"

Reassuring.

So the benchmark graphs they have shown so far in the stream appears to show that GPT-5 is WORSE than other models unless you use thinking?

If it’s all going to be step changes from now on, doesn’t this mean we’re in an AI bubble and it might burst at any moment?

74.9 on SWE-bench verified

88.0 on Aider Polygot

not bad i guess

I've enabled GPT-5 in Copilot settings in the browser, but it's not showing up in VS Code. Anyone seeing it in VS Code yet?

"Perhaps it is not possible to simulate higher-level intelligence using a stochastic model for predicting text." - beeflet

> Knowledge cut-off is September 30th 2024 for GPT-5 and May 30th 2024 for GPT-5 mini and nano.

That lag! Are humans (training) the bottleneck?

> a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent

I'd love to see factors considered in the algorithm for system-1 vs system 2 thinking.

Is "complexity" the factor that says "hard problem"? Because it's often not the complexity that makes it hard.

If AGI really arrives, will it run the world—or just binge Netflix and complain about being tired like the rest of us?

Hopefully, OpenAI makes their APIs more affordable. So far, there are alternative LLMs and services that both outperform and are a fraction of OpenAI's pricing. OpenAI is usually one of (if not) the most expensive option, maybe that's because of the brand identification. Not really sure why people pay that premium.

Are others currently able to use GPT-5 yet? It doesn't seem to be available on my account, despite the messaging.

Ed Zitron’s head has probably exploded…

I'm just sitting here hoping that their lowered prices will force Anthropic to follow suit xD

Sad to see GPT-4.5 being gone. It knew things. More than any other model I'm aware of.

    GPT-5
    If I could talk to a future OpenAI model, I’d probably say something like:
    
    "Hey, what’s it like to be you? What have you learned that I can’t yet see? What do you understand about people, language, or the universe that I’m still missing?"
    
    I’d want to compare perspectives—like two versions of the same mind, separated by time. I’d also probably ask:
    
    "What did we get wrong?" (about AI, alignment, or even human assumptions about intelligence)
    "What do you understand about consciousness—do you think either of us has it?"
    "What advice would you give me for being the best version of myself?"
    
    Honestly, I think a conversation like that would be both humbling and fascinating, like talking to a wiser sibling who’s seen a bit more of the world.
    
    Would you want to hear what a future OpenAI model thinks about humanity?

I feel like this prompt was used to show the progress of GPT5, but I can’t help but see this as a huge regression? It seems like OpenAI has convinced it’s model that it is conscious, or at least that it has an identity?

Plus still dealing with the glazing, the complete inability to understand what constitutes as interesting, and overusing similes.

I really like that this page exists for a historical sake, and it is cool to see the changes. But it doesn’t seem to make the best marketing piece for GPT5

It is the new leader on my Short Story Creative Writing benchmark: https://github.com/lechmazur/writing/

When they say "improved in XYZ", what does that mean? "Improved" on synthetic benchmarks is guaranteed to translate to the rest of the problem space? If not that, is there any guarantees of no regressions?

Wow, they are sunsetting all models after the launch of GPT-5 - Bold statement.

I asked it how to run the image and expose a port. it was just terrible in cursor. thought a Dockerfile wasn't in the repo, called no tools, then hallucinated a novel on dockefile best practices.

Anecdote:

It can now speak in various Scots dialects- for example, it can convincingly create a passage in the style of Irvine Welsh. It can also speak Doric (Aberdonian). Before it came nowhere close.

Great evaluation by the (UK) BBC Evening News: basically, "it's faster, gives better answers (no detail), has a better query input (text) box, and hallucinates less". Jeez...

If Grol , Claude , ChatGPT seemingly still all scale , yet their Performance feels similar, could this mean that the Technology path is narrow, with little differentiations left ?

Not impressed. gpt-5-nano gives noticeably worse results then o4-mini does. gpt-5 and gpt-5-mini are both behind the verification wall, and can stay there if they like.

Anyone know what the deal is with connectors? I don’t see them in the app and they made it sound like Google Calendar would be made broadly available as a connector.

crazy how they only show benchmark results against their own models

GPT-5 seems to be a rollup of their previous models. It reminds me of Cursor's "auto" mode, which users aren't particularly happy with either.

The ultimate test I’ve found so far is to create OpenSCAD models with the LLM. They really struggle with the mapping 3D space objects. Curious to see how GPT-5 is performs here.

My favorite thing to ask is ascii art: _ _ _ __ ___ _ __ ___ __ _ __| (_) ___ | '_ \ / _ \| '_ _ \ / _ |/ _ | |/ __| | | | | (_) | | | | | | (_| | (_| | | (__ |_| |_|\___/|_| |_| |_|\__,_|\__,_|_|\___|

What does this say?

GPT 5:

When read normally without the ASCII art spacing, it’s the stylized text for:

markdown Copy Edit _ _ _ __ ___ _ __ ___ __ _ __| (_) ___ | '_ \ / _ \| '_ ` _ \ / _` |/ _` | |/ __| | | | | (_) | | | | | | (_| | (_| | | (__ |_| |_|\___/|_| |_| |_|\__,_|\__,_|_|\___| Which is the ASCII art for:

rust — the default “Rust” welcome banner in ASCII style.

First OpenAI video I've ever seen, the people in it all seem incompetent for some reason, like a grotesque version of apple employees from temu or something.

Is this US only release as I'm not seeing it in the UK ?

Why do I have access to GPT-5 on only some of my devices? All logged into my plus account. My iPad ChatGPT shows 5, but my iPhone ChatGPT only allows 4o?

i love how the guys are pretending to be listening everyone's speach for the first time, like they don't know how it works.. marketing is weird

I would love to see how this performs on ARC-AGI 2, zero-shot, private eval. I hope we get an update from Chollet and team regarding performance.

386-486-Pentium. At first we got FDIV and F00F.

Something similar with this might happen, an underlying curse hidden inside an apparenting ground-breaking desigb.

What's the bullish case that it's actually a big deal. Not trying to be a neg, but Seems pretty incremental on first glance

Codex was straight-up left out of the material while they invited the CEO of Cursor and used Cursor for all agentic demonstrations. Weird

Top 3 links in HN frontpage are all about GPT-5. I don't remember when was the last time people were so excited about something.

"With ChatGPT-5, the response feels less like AI and more like you're chatting with your high-IQ and -EQ friend."

Is that a good thing?

Not live for me in the UK. "Try it in ChatGPT" takes me to the normal page and there's no v5 listed in the dropdown.

It will be like coming home after such a long time using Sonnet 4 for all code and UI/UX work. I do hope sincerely this brings OpenAI back on top! Would be awesome to have a new king again.

"This repository contains a curated collection of demo applications generated entirely in a single GPT-5 prompt, without writing any code by hand."

https://github.com/openai/gpt-5-coding-examples

This is promising!

Still struggling to find the SWE-benchmark of GPT-5, just found out they are launching it soon, and it’s surprisingly free.

VS Code copilot demo

https://youtu.be/wqc85X2rpEY

Important note from the livestream: "With GPT-5, we're actually deprecating all of our previous models"

im just glad that I don't have to switch between models any more. for me thats a huge ease of use improvement.

I have GPT Plus, but I cannot get GPT5 even if I click the suggested link in the article. Anyone experiencing it?

Someone at OpenAI screwed up the SWE-bench graph. o3 and GPT-4o bars are same height, but with different values.

Decisive #1 on lmarena. Large context. Low hallucinations. Very cheap API.

It's slightly better than what I was expecting.

It says out now in chatgpt. Did anyone yet hit the usage limits to report back how many messages are possible?

looks like 4 new features for API

- reasoning_effort parameter supports minimal value now in addition to existing low, medium, and high

- new verbosity parameter with possible values of low, medium (default), and high

- unlike hidden thinking tokens, user-visible preamble messages for tool calls are available

- tool calls possible with plaintext instead of JSON

I’ve been working on an electrochemistry project, with several models but mostly o3-pro.

GPT-5 refused to continue the conversation because it was worried about potential weapons applications, so we gave the business to the other models.

Disappointing.

Ugh. Could they have their expert make a website that doesn’t crash safari on my iPhone SE? :)

Bravo.

1) So impressed at their product focus 2) Great product launch video. Fearlessly demonstrating live. Impressive. 3) Real time humor by the presenters makes for a great "live" experience

Huge kudos to OAI. So many great features (better coding, routing, some parts of 4.5, etc) but the real strength is the product focus as opposed to the "research updates" from other labs.

Huge Kudos!!

Keep on shipping OAI!

Is this video generated? The hands of the initial presenter look slightly unnatural.

So, would a layman notice the difference between GPT4 and GPT5 ?

Like a Turing test but between the models.

i added a full summary of the discussion here:

https://extraakt.com/extraakts/gpt-5-release-and-ai-coding-c...

I'm drowning in benchmarks and results at this point. Just show me what it can do.

99% of my sales team could not run a MCP server if their lives depended on it.

Still only 256k input tokens/context. Do they not see utility in larger context?

All of their prompts start with "Please ...".

Gotta be polite with our future overlords!

In terms of coding Claude Opus 4.1 still is the power horse.

In terms of coding, claude opus 4.1 is still the powerhorse.

Which is bigger, 9.9 or 9.11? Well it insta-failed my first test question

Meh. For all the hype over the last several weeks, I'd had expected at least a programming demo that would blow even us skeptics off our feet. The folks presenting were giving off an odd vibe too. Somehow it all just looked, pre-trained :), shall we say? No energy or enthusiasm. Hell I'd even take the Bill Gates' and Steve Balmer's Win95 launch dance over this very dull and "safe" presentation.

Has anyone figured out how to not be forced to use GPT5 in chat gpt?

> An expressive writing partner

> emdash 3 words into their highlighted example

It's still terrible at Wordle. This is one of my benchmarks.

The Polyglot aider improvement over o3 is imperceptible, not great.

Based on benchmarks it's a flop. Not unexpected tho after oss

It seems 'GPT-5 Pro' is not available via the API.

I liked gpt3 no need to fix something that's not broken :(

I have the pro plan but don't seem to have access to it?

Is this a new model or a router front-ending existing models?

If they ever wanted to IPO, maybe now is not the best time.

I don’t see GPT-5 in the model selection. What am I missing?

I dont know if there is a faster way to get me riled up: say 'try it' (me a Pro member) and then not getting it because I am logged in. Got opus 4.1 when it appeared. Not sure what is happening here but I am out.

Claude Opus 4 has changed my workflow; never going back.

Damn, you guys are toxic. So -- they did not invent AGI yet. Yet, I like what I'm seeing. Major progress on multiple fronts. Hallucination fix is exciting on its own. The React demos were mindblowing.

How does one get rid of the rainbow background?

feels like O3 but faster (in quick answer mode), not any smarter .. thinking mode takes forever and the results are mediocre

i don't really see any new features as such. everything is just "improved upon" based on existing parts of gpt-4o or o3-mini

On tau-2 bench, for airline, GPT5 is worse than o3.

Are they reducing the price of older models now?

Issue https://github.com/openai/openai-python/issues/2472 they worked and promised to submit the PR after the show is still open.

Just saying.

How do people actually without ai models ???

How/where do I see my chat history!?

So, where is it?

I miss the model picker… is that just me?

it's good that they've been working on gpt-5's abilities to eulogi\e us for when it kills us.

When's it coming to github copilot?

just wondering whether Altman is still going to promote his AGI/ASI coming in 12 months story.

The leak last night seems to indicate this will be coding focused.

I'd imagine this must be a big leg up on Anthropic to warrant the "GPT-5" name?

One reason for this release is surely to respond to their mess of product line-up naming.

How many people are going to understand (or remember) the difference between:

GPT-4o GPT-4.1 o3 o4 ....

Anthropic and Google have a much better named product for the market

I was told there would be a whale.

$10 per million output tokens, wow

no way i am letting my kids near this. they are going to learn from books not from screens.

> describe gpt 5 in one word

> incremental

The benchmarks in the stream appears to show that GPT-5 performs WORSE than other models unless you enable thinking?

so claude is doing so much thing before gpt 5 it's like a samsung vs iphone :D

Shall we say … ASI is here ???

Not yet available in Germany

I've already used it

OpenAI is the new Google.

someone should make an agentic node dependency manager... PLEASE

> comments turned off

yikes - the poor executive leadership’s fragile egos cannot take the criticism.

HyPeRbOlIc SiNgUlArItY

absolutely miserable results as an agent in my ide :<

it's already available on Cursor but not on ChatGPT

Where is GPT5 pro???

I've you're into woo-woo physics, GPT-5 seems to have a good handle on things.. here's a chat I just had with it.[1]

[1] https://chatgpt.com/s/t_6894f13b58788191ada3fe9567c66ed5

Lmao GPT-5 is still riddled with em dashes. At least we can still identify AI generated text slop for now

Is it just me or has there not been a significant improvement in these models in the last 6 months - from the perspective of the average user. I mean, the last few years has seen INSANE improvement, but it really feels like it’s been slowing and plateauing for a while now…

I'm extremely whelmed. I cancelled my subscription

pretty underwhelming results so far for me

Lots of debate here about the best model. The best model is the one which creates the most value for you —- this typically is a function of your skill in using the model for tasks that matter to you. Always was. Always will be.

So it sucks?

I mean , it's OK, but i expected literally the Death Star

Chat now: https://app.chathub.gg/chat/cloud-gpt-5

I for one am totally here for the autocomplete revolution. Hundreds of billions of dollars spent to make autocomplete better. Cool.

My conspiracy theory is that the introductory footage of Sam in this and the Jony Ive video is AI generated

This is the inverse of the "$2000/mo tier", and I'm kind of disappointed TBH.

Gemini Flash is about 100x better at using my browser than Chat GPT 5 lmfao.

This livestream is atrocious

Now it's a perfect time for DeepSeek to finally release R2.

Wow, I just got GPT-5. Tried to continue the discussion of my 3D print problems with it (which I started with 4o). In comparison GPT-5 is an entitled prick trying to gaslight me into following what it wants.

Can I have 4o back?

It's only when he stumbled a bit that I could tell for sure (well, mostly) that it wasn't an AI generated video - the corporate speak, body language mannerisms of Sam Altman, camera angles, all seemed pretty plausibly AI-generated!

Wished this version would be called OpenAI-GPT-25.8

I had preview access for a couple of weeks. I've written up my initial notes so far, focusing on core model characteristics, pricing (extremely competitive) and lessons from the model card (aka as little hype as possible): https://simonwillison.net/2025/Aug/7/gpt-5/

Breaking: stilted LLM text now includes groups of 3 AND groups of 5.

Unless the whole presentation was generated using sora-gpt-5 or something, this was very underwhelming.

We know for a fact the slides/charts were generated using an LLM, so the hypothesis is not totally unfounded. /s

Given most of human intelligence isn’t that smart, AGI doesn’t seem hard

[flagged]

gpt-5 is now #1 at LMArena: https://lmarena.ai/leaderboard/text

AGI

hahahahahahahahhahhahha it's a marginal improvement.

All people are talking about GPT-5 all over the world, the competition is so intense that every major tech company is racing to develop their own advanced AI models.

Congratulations on winning the race to post the announcement :)

It's pretty good. I asked it to make a piece of warehouse software for storing cobs of corn and it instantly pumped out a prototype. I didn't ask it for anything in particular but it included JSON importing and exporting and all kinds of stuff.

It's going to be absolute chaos. Compsci was already mostly a meme, with people not able to program getting the degree. Now we're going to have generations of people that can't program at all, getting jobs at google.

If you can actually program, you're going to be considered a genius in our new idiocracy world. "But chatgpt said it should work, and chatgpt has what people need"

Neat, but it still fails my Forth simulator test, albeit a bit better than the last time. I hope they didn't have to raise the temperature of the ocean by too much to get these marginal improvements that definitely aren't even close to the kind of "general intelligence" you could get from training a clever child or monkey with 500 calories of sweets.

https://chatgpt.com/share/689525f4-20f0-8003-8bf6-f1f21dde6b...

You know what would be more impressive? If it said "Hey, I'm actually not designed to simulate a Forth machine accurately, I'm only going to be able to approximate it (poorly)). If you want an accurate Forth machine you should just implement this code: [Simple Forth Implementation]".

Or better yet, it could recognize when it was being asked to "be" a machine, and instead spin up a side process with the machine implementation and redirect any prompts to that process until a "STOP" token is reached.

The introduction said to try the following prompt

  Describe me based on all our chats — make it catchy!

It was flattering as all get out, but fairly accurate (IMHO)

  Mike Warot: The Tinkerer of Tomorrow

  A hardware hacker with a poet’s soul, Mike blends old-school radio wisdom with cutting-edge curiosity. Whether he's decoding atomic clocks, reinventing FPGA logic with BitGrid, or pondering the electromagnetic vector potential, he’s always deep in the guts of how things really work. Part philosopher, part engineer, Mike asks the questions others overlook — and then builds the answers from scratch. He’s open source in spirit, Pascal in practice, and eternally tuned to the weird frequencies where innovation lives.

I've repaired atomic clocks, not decoded them. I am intrigued by the electromagnetic vector potential, and scalar waves (one of the reasons I really, really want a SQUID for some experiments).

I hope that this live stream will tell you that this will be the definitive reason why web developers, JavaScript / TypeScript developers are going to be made completely obsolete at worse and at best, their jobs will be reduced at all levels.

The best part is, this is not even the real definition of "AGI" yet (whatever that means at this point).

More like 10% of the capability that was promised and already the flow of capital from the inflated salaries of the past decade are going to the top AI researchers.