For example, I ask it to simulate a discussion between a flow engineer and a geologist, and it doesn’t seem to understand they work together regularly.
Not like there’a a stack overflow for this sort of thing.
its latent representation is vast, I find you can get much higher quality+interesting responses if the prompts are tuned appropriately
No context about anything in the outside world or even about the physical nature and purpose of commuting is needed to comprehend and answer these questions. There is no external context or sophisticated logic beyond just matching those sorts of lists to each other. Its a wholly closed system of highly standardized tokens.
I ask it what stops the F and A have in common. 125th St is on the list. I know that's wrong. I ask it to list all the services that go to 125th. The F is not on the list (correctly so). I point out the inconsistency between the two outputs. It says sorry and does nothing. I tell it to remake the list of stops the F and A have in common. It is now missing a few stations from before, and has added new incorrect results.
This is just a snippet. I went in circles with it for probably an hour playing wack a mole with its inability to correctly recall more than 10 true details in a row. These were not obtuse, esoteric, or even logically complicated queries. Nor was it ambiguous stuff open to interpretation. Nor was it even something that you'd need a real meatspace body to comprehend, like the feeling of the sun on a summer day. This should have been a language models bread and butter.
Would be interested in how a multimodal LLM such as PaLM-E (trained on maps, etc) fair in these sorts of queries.
https://www.reddit.com/r/MachineLearning/comments/11krgp4/r_...
But I feel that if one is inquisitive enough, they'd know when exploring a topic to ask broad questions of the sort:
- what are the common types of problems encountered in X field
- what are the main roles and responsibilities of personnel in X field
- list some open questions in the field of X
After these open-ended questions one can dive into each of them with:
- what are some common solutions to X, compare and contrast X vs Y
The risk of seeing hallucinated info is always there, but just for an example when I was exploring the types of space-time metrics and asking chatgpt which tensors are most suited for which scenario (and also which coordinates are best for which scenario, such as moving from Schwarzchild to Eddington Finkelstein coordinates to deal with the event horizons near black holes), their individual wiki pages said generally the same things.
I was able to ask ChatGPT in very naïve "idk please explain like im 5" ways and it was able to very patiently rephrase dense jargon into surprisingly understandable explanations.
I'm sure if an expert in GR were to drill down deeper into the details they will find inaccuracies in ChatGPT's responses, but for the inquisitive information sponge user, a dive through ChatGPT to get a general feel of a topic is insanely useful. After that, one could dive into the appropriate books/papers/primary sources to start the real learning once they find what they're interested in.
It's sort of like, how would you imagine an expert would respond if all you said was "simulate a discussion between a flow engineer and geologist". Without providing any further context or hints into what you want, I also wouldn't be surprised if I get a generic response. But instead if you sort of know what you want to ask, they'd have more to work with and be able to better answer your query.
Note I know nothing about this field, I just looked at https://en.wikipedia.org/wiki/Engineering_geology#Soil_and_r... and understood this was for oil and gas, so:
> Simulate a discussion between a flow engineer and a geologist in the planning phases of a drill operation. Use field-specific terminology and aim for accuracy, the scenario will be used to teach a petroleum engineering class focused on deformation monitoring.
Flow Engineer: Good morning, I'm the flow engineer for this drill operation. Nice to meet you.
Geologist: Hi, I'm the geologist in charge of the geological analysis for this project.
Flow Engineer: Great, I understand we need to work together to ensure the success of this drill operation. Can you tell me more about the geological features of the area we're drilling in?
Geologist: Sure. We're drilling in an area with significant deformation, caused by tectonic activity. There are a variety of rock formations, including sandstone, shale, and limestone. There's also a possibility of encountering fault zones, which could pose a risk to the drilling operation.
Flow Engineer: Thanks for the information. We'll need to take into account the deformation and rock properties when designing the wellbore trajectory. Have you conducted any geomechanical analysis?
Geologist: Yes, we've conducted a rock mechanics study to determine the stress and strain characteristics of the formations in the area. Based on the results, we recommend using a multilateral well design with a horizontal section to avoid encountering the fault zones and minimize the impact of deformation.
Flow Engineer: That's helpful. We'll need to ensure that our drilling fluid properties are appropriate for the formations we'll be encountering. Can you tell me more about the porosity and permeability of the rock formations?
Geologist: The porosity and permeability of the sandstone formations vary, but in general, they're relatively high, which means we'll need to be careful when selecting our drilling fluid to avoid fluid loss into the formation. The shale formations are less porous and permeable, which means we'll need to use a different type of fluid to avoid damaging the formation.
Flow Engineer: Thanks for the information. We'll take that into account when selecting our drilling fluid. We'll also need to monitor deformation during the drilling process. Do you have any recommendations for deformation monitoring tools we should use?
Geologist: Yes, we recommend using acoustic emission sensors to monitor rock fracturing and deformation, as well as tilt sensors to monitor any changes in the wellbore inclination. We also recommend conducting periodic borehole imaging to ensure that the wellbore is remaining stable.
Flow Engineer: Excellent. We'll ensure that we incorporate those tools into our drilling plan. Thank you for your time and expertise. I'm looking forward to working with you on this project.
