21–30 of 461 posts
its best to tell them how you want the code written.
Something major missing from the LLM toolkit at the moment is that it can't actually run (and e.g. test or benchmark) its own code. Without that, the LLM is flying blind. I guess there are big security risks involved in making this happen. I wonder if anyone has figured out what kind of sandbox could safely be handed to a LLM.
It'd be great if it could describe the performance of code in detail, but for now just adding a skill to detect if a bit of code has any infinite loops would be a quick and easy hack to be going on with.
Using the tool in this way is a bit like mining: repeatedly hacking away with a blunt instrument (simple prompt) looking for diamonds (100x speedup out of nowhere). Probably a lot of work will be done in this semi-skilled brute-force sort of way.
Sure, you'll get better results with an LLM when you're more specific, but what's the point then? I don't need AI when I already know what changes to make.
Using the tool in this way is a bit like mining: repeatedly hacking away with a blunt instrument (simple prompt) looking for diamonds (100x speedup out of nowhere). Probably a lot of work will be done in this semi-skilled brute-force sort of way.
If I were a CS student cramming for interviews, I might be dismayed to see that my entire value proposition has been completely automated before I even enter the market.
Earlier quoted context omitted.
It'd be great if it could describe the performance of code in detail, but for now just adding a skill to detect if a bit of code has any infinite loops would be a quick and easy hack to be going on with.
Is reliably detecting if code has any infinite loops feasible? Sounds like the halting problem.
The more interesting question IMO is not how good the code can get. It is what must change for the AI to attain the introspective ability needed to say "sorry, I can't think of any more ideas."
Wow, what a great post. I came in very skeptical but this changed a lot of misconceptions I'm holding. One question: Claude seems very powerful for coding tasks, and now my attempts to use local LLMs seem misguided, at least when coding. Any disagreements from the hive mind on this? I really dislike sending my code into a for profit company if I can avoid it. Second question: I really try to avoid VSCode (M$ concerns…
Intellij has a new feature that lets you prompt within your code that is pretty neat too, but I'm missing the Composer/apply feature of cursor still
its best to tell them how you want the code written.
At that point isn't it starting to become easier to just write the code yourself? If I somehow have to formulate how I want a problem solved, then I've already done all the hard work myself. Having the LLM just do the typing of the code means that now not only did I have to solve the problem, I also get to do a code review.
Something major missing from the LLM toolkit at the moment is that it can't actually run (and e.g. test or benchmark) its own code. Without that, the LLM is flying blind. I guess there are big security risks involved in making this happen. I wonder if anyone has figured out what kind of sandbox could safely be handed to a LLM.
There are also large applications like https://devin.ai/ or https://github.com/AI-App/OpenDevin.OpenDevin