> A recent study by the Institute of Software, Chinese Academy of Sciences, Microsoft, and others, suggest that the performance of LLMs can be enhanced through emotional appeal.
> Examples include phrases like “This is very important to my career” and “Stay determined and keep moving forward”.
Of course the top LLMs change every few months, so your mileage may vary.
> Is there a human out there who would just magically type all the right things - no errors - first try?
If they know what they're doing and it's not an exploratory task where the most efficient way to do it is by trial and error? Quite a few. Not always, but often.
That skill seems to have very little value in today's world though.
I guess, like a lot of other sports at the college level, having a reputation that attracts the best competitive programmers (and a great coach to go along with it) doesn't hurt:
https://en.wikipedia.org/wiki/Andrey_Stankevich
> The fact that is is needed at all of course highlights a weakness in the language. The import statements themselves should be able to convey all information about dependencies
What languages convey the version of the dependencies in a script’s import statements?
These models have proven to develop incredible abilities through pattern matching on massive text data, so I wouldn’t be too quick to dismiss the limits of what they could do.
Having them use specialized tools would probably be more effective (e.g. have the reasoning LLM use the DNA LLM), but in the long term with scale… who knows? The bitter lesson keeps biting us every time we think we know better.
> As the confidence of advice, how much the rates of the mistakes are different between human lawyers and the latest GPT?
Notice I am not talking about "rates of mistakes" (i.e. accuracy). I am talking about how confident they are depending on whether they know something.
It's a fair point that unfortunately many humans sound just as confident regardless of their knowledge, but "good" experts (lawyers or otherwise) are capable of saying "I don't know (let me check)", a feature LLMs still struggle with.
> amount of data you'd need to learn in order to give descent law advice on a spot?
amount of data you'd need to learn to generate and cite fake court cases and give advice that may or not be correct with equal apparent confidence in both cases
> Should we not mimic our biology as closely as possible rather than trying to model how we __think__ it works (i.e. chain of thought, etc.).
Should we not mimic migrating birds’ biology as closely as possible instead of trying to engineer airplanes for transatlantic flight that are only very loosely inspired in the animals that actually fly?
https://jurgengravestein.substack.com/p/why-you-should-total...
> A recent study by the Institute of Software, Chinese Academy of Sciences, Microsoft, and others, suggest that the performance of LLMs can be enhanced through emotional appeal.
> Examples include phrases like “This is very important to my career” and “Stay determined and keep moving forward”.
Of course the top LLMs change every few months, so your mileage may vary.