Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Making o1, o3, and Sonnet 3.7 hallucinate for everyone

bengarcia.dev

Post reply on HN
Print view View original

131–140 of 233 posts

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#131

Post by miningape »

johnisgood wrote: post #104
miningape wrote: post #7

Earlier quoted context omitted.

Any time I ask anything, LLMs are often bad. inb4 you just aren't prompting correctly

Yeah, you probably are not prompting properly, most of my questions are answered adequately, and I have made larger projects with success, too; with both Claude and ChatGPT.

What I've found is that the quality of an AI answer is inversely proportional to the knowledge of the person reading it. To an amateur it answers expertly, to an expert it answers amateurishly.

So no, it's not a lack of skill in prompting: I've sat down with "prompting" "experts" and universally they overlook glaring issues when assessing the how good an answer it was. When I tell them where to press it further it breaks down with even worse gibberish.

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#133

Post by johnisgood »

mvdtnz wrote: post #132
johnisgood wrote: post #110

Earlier quoted context omitted.

In my case the maximum was ~3k LOC.

That's not just small, it's utterly miniscule. It's most certainly not large.

Depends. 3k is pretty much enough for a fully-featured XY.

So no context, and differences of the definition of "large".

Perhaps if you come from Java, then yeah.

shrugs

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#134

Post by johnisgood »

miningape wrote: post #131
johnisgood wrote: post #104

Earlier quoted context omitted.

Yeah, you probably are not prompting properly, most of my questions are answered adequately, and I have made larger projects with success, too; with both Claude and ChatGPT.

What I've found is that the quality of an AI answer is inversely proportional to the knowledge of the person reading it. To an amateur it answers expertly, to an expert it answers amateurishly. So no, it's not a lack of skill in prompting: I've sat down with "prompting" "experts" and universally they overlook glaring issues when assessing the how good an answer it was. When I tell them where to press it further it br…

I know what I want to do and how to do it (expert), so the results are good, for me at least. Of course I have to polish it off here and there.

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#135

Post by spookie »

andrepd wrote: post #92
dominicq wrote: post #5

ChatGPT used to assure me that you can use JS dot notation to access elements in a Python dict. It also invented Redocly CLI flags that don't exist. Claude sometimes invents OpenAPI specification rules. Any time I ask anything remotely niche, LLMs are often bad.

My rule of thumb is: is the answer to your question on the first page of google (a stackoverflow maybe, or some shit like geek4geeks)? If yes GPT can give you an answer, otherwise not.

Exactly the same experience.

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#137

Post by saurik »

What I honestly find most interesting about this is the thought that hallucinations might lead to the kind of emergent language design we see in natural language (which might not be a good thing for a computer language, fwiw, but still interesting), where people just kind of thing "language should work this way and if I say it like this people will probably understand me".

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#138

Post by andix »

xmprt wrote: post #122
simion314 wrote: post #117

Earlier quoted context omitted.

>most LLMs are great for spitting out some code that fulfills 90% of what you asked for. That's sometimes all you need. But we all know that the last 10% usually take the same amount of effort as the first 90%. The issue is if you have an LLm write for you 10k lines of code, where 100 lines are bugged. Now you need to debug the code you did not write and find the bugged code, you will waste similar amount of time. Th…

In my experience using LLMs, the 90% is less about buggy code and more about just ignoring 10% of the features that you require. So it will write code that's mostly correct in 100-1000 lines of code (not buggy) but then no matter how hard you try, it won't get the remaining 10% right and in the process, it will mess up parts of the 90% that was already working or end up writing another 1000 lines of undecipherable co…

Exactly my experience. It's always missing something. And the generated code often can't be extended to fulfil those missing aspects.

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#139

Post by DrammBA »

foundry27 wrote: post #15
nokun7 wrote: post #6

[flagged]

It’s always a touch ironic when AI-generated replies such as this one are submitted under posts about AI. Maybe that’s secretly the the self-reflection feedback loop we need for AGI :)

So strange too, their other comments seem normal, but suddenly they decided to post a gpt comment.

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#140

Post by HarHarVeryFunny »

andix wrote: post #30

I've got a lot of hallucinations like that from LLMs. I really don't get how so many people can get LLMs to code most of their tasks without those issues permanently popping up.

What TFA was talking about didn't really seem like an hallucination - just a case of garbage in-garbage out. Normally there are more examples of good/correct data in the training set than bad, so statistically the good wins, but if it's prompted for something obscure maybe bad is all that it has got.

Common coding tasks are going to be better represented in the training set and give better results.

Post reply on HN