Imagine is a good word to use. Before offering a solution, understand the problem first - is "debugging speed" a problem that needs solving, in this case?
Much more likely is that it would hallucinate a plausible sounding but incorrect answer and send intermediate and junior engineers on a wild goose chase
if an LLM is capable enough to be used this way it would be used to generate scenarios for the people who would otherwise have to be the ones to generate them. those people would then evaluate the scnearios. those people would then be in a position to decide if the LLM saves them time.
Are there enough open source aero engineering projects to give the current ai approaches a remotely plausible amount of training data?
Imagine is a good word to use. Before offering a solution, understand the problem first - is "debugging speed" a problem that needs solving, in this case?
Much more likely is that it would hallucinate a plausible sounding but incorrect answer and send intermediate and junior engineers on a wild goose chase
if an LLM is capable enough to be used this way it would be used to generate scenarios for the people who would otherwise have to be the ones to generate them. those people would then evaluate the scnearios. those people would then be in a position to decide if the LLM saves them time.
> a plausible sounding but incorrect answer
That is an incorrect but plausible hypothesis. Do you really think that people can't make such mistakes?
If you want to say that people have understanding, then define understanding in an operationalizable way first.
It doesn't mean that I would recommend a general-purpose AI model without additional training to do a fault analysis.
>That is an incorrect but plausible hypothesis. >Do you really think that people can't make such mistakes?
Where did I say that? You just pulled that out of nowhere and then refuted it - strawman https://en.wikipedia.org/wiki/Straw_man
6 replies →