Hacker Newsnew | past | comments | ask | show | jobs | submit | vrighter's commentslogin

I also don't get the point. So what if the output format is different? It's still just as hallucination prone as before, right?

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

But isnt the whole point of Jev that "we trained it so you dont have to"? Yet it make such a simple mistakes still.

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

it doesn't work that way though

how do you do FMAs then? You're making one operation cheaper, but making the other one expensive.

“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.”

so, were everything to be coated in this stuff, what would that do in heavily built city environments? Make being outside even more intolerable?

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"


it's so they can claim to the investors that they were forced to slow downc and keep e scam going on for jus a bit longer

C11 is the c language version. misra C is a set of guidelines for robust code when lives are on the line.

One rule is "no malloc after initialization". so no, you probably aren't. Nor should you be. misra is intended for the programmerc not the compiler


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?

you hit the nail right on the head!

"chain of thought"'s whole point is to leave future messages to themself, because they are memoryless. Just the latest marketing spin

they will eventually open preorders, then increase the prices for the prepaid orders, and then actually deliver the dancer in a robot suit

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: