I was watching some youtube hype demo of it to pick items (each an emoji) from a pile according to questions. One of the questions was: "what can a magnet attract?" and it picked like 8 metal items, while a literal magnet was left unpicked. Ofc the video was too busy praising it to notice. Was all I needed to see
That it can make mistakes? That’s expected, it deal with plausibility like other models no? You would need to look at the actual response and the assigned probabilities to evaluate. Generally demos are not a great way to evaluate a technology, it’s a way to get hype but the next step is to actually look at the details
Yes, I don’t think hallucinations will ever go away. But because it doesn’t work with language the type of hallucinations aren’t too comparable to LLMs. But it is still a risk of course, whatever system you design should take that in consideration
“You’re making one operation cheaper, but making the other one more expensive” is the wrong way around. Say it this way: “You’re making one operation more expensive, but the other one cheaper.”
Autocomplete with an LSP is fine. That's always correct.
Autocomplete with an LLM, which generates snippets for you is just a lubricated version of "copy and paste back and forth between chat window and code window"
He's emitting C as an intermediate form. I'm asking if the C that's emitted is meeting MISRA or any other recognized standard for secure and robust C code.
you can't have a compiler automatically generate misra C. Because misra is a set of programmer discipline guidelines. How would you automatically convert a program that does dynamic allocation into one that preallocates all memory up front in the init phase?
reply