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

A recent experience with ChatGPT 5.5 Pro

gowers.wordpress.com

Post reply on HN
Print view View original

531–540 of 558 posts

Re: A recent experience with ChatGPT 5.5 Pro

#531

Post by jesgran »

kannanvijayan wrote: post #271
jillesvangurp wrote: post #116

Earlier quoted context omitted.

Exactly, if I generate a large chunk software, I'm going to have expectations about what it will do, how it will do it, etc. You don't just accept the statement that "it's done" for fact but you start looking for evidence. A scientific approach here is to look to falsify the statement. You start asking questions, running tests, experiments, etc. to prove the notion that it is done wrong. And at some point you run out…

I can speak towards building large-scale systems from scratch with these tools. I've been working since late last year on a project that was barely a tech demo, and the progression of development on that project has seen me go from leveraging co-pilot autocomplete at the start, to full-on vibecoding 100% of the new additions. I have reasonable eng chops I'd like to think - I have been a senior IC for a while on a rea…

[dead]

Re: A recent experience with ChatGPT 5.5 Pro

#532

Post by nxobject »

pixl97 wrote: post #518
nozzlegear wrote: post #309

Earlier quoted context omitted.

Until you or I can actually use Mythos in Claude without an nda or other strings attached, Mythos is not released and is just an effective marketing tool for Anthropic.

At least to me this is a pretty sour grapes take. There are all kinds of released products that are expensive or need an NDA. You're just too poor to afford it. But make no mistakes there are governments using this in mass and likely against you.

I think that’s worthy of at least sour grapes, too.

Re: A recent experience with ChatGPT 5.5 Pro

#533

Post by wrer »

baq wrote: post #505
2wdfsd wrote: post #431

Earlier quoted context omitted.

Private market dynamics are not the same buddy.

Everyone owns them at this point and Google is outright public.

No youre missing the point of the poster - disclosures in private markets are different than public, especially in the context of large commitments - the company has no choice.

Re: A recent experience with ChatGPT 5.5 Pro

#534

Post by dpweb »

Don’t quite agree with the implication that if the answer to a problem is readily available (from an LLM) there is no use in the struggle to find the solution.

However I think it’s very important to approach such questions objectively, or at least self uninterested, and not as one who’s worried about one’s job or sense of self worth threatened by LLM technology.

The value is in the development of one’s own mental faculties. In math classes they tell you you have to work the problems. Even if LLMs become capable of solving entire classes of problems that that set expands over time, the value in developing one’s ability never goes out of style.

Re: A recent experience with ChatGPT 5.5 Pro

#535

Post by jfaat »

y1n0 wrote: post #404
Jweb_Guru wrote: post #389

This jives with what I've experienced in the brief time I had access to 5.5 Pro. It's the very first LLM that I feel like I can wrangle into solving tedious, but straightforward, problems correctly. It still makes a ton of mistakes and needs to be very rigidly guided, but it does a pretty good job of tracing its own reasoning and correcting itself in a way that the other models do not. The downside (not noted in the…

> This jives with what I've experienced Just as an fyi, the word you are looking for is jibes. Jive is something else entirely.

I'm going to start using malapropisms so people know I didn't use an llm to write things

Re: A recent experience with ChatGPT 5.5 Pro

#536

Post by DoctorOetker »

illiac786 wrote: post #122
ziotom78 wrote: post #62

I am a physics professor and often use Gemini to check my papers. It is a formidable tool: it was able to find a clerical error (a missing imaginary unit in a complex mathematical expression) I was not able to find for days, and it often underlines connections between concepts and ideas that I overlooked. However, it often makes conceptual errors that I can spot only because I have good knowledge of the topic I am di…

Using the word “Mentoring” is anthropomorphic and subconsciously makes you think it will learn. It does not, and it is for the human brain a formidable task to remember that something as smart as an LLM does not learn. I keep catching myself making the same mistake. It’s also because it is so annoying to have to manage the memory of the LLM with custom prompts/instructions manually. I have not yet played with the lon…

> ... that something as smart as an LLM does not learn.

what? training is learning, as long as weights are available continual learning is perfectly feasible: just keep training the LLM with the user corpus alternated with a frozen version to prevent catastrophic drift / collapse.

it's not because model providers don't want to provide user specific continual learning, that we don't know how to do it.

it would be a lot more expensive to host user-specific model weights, and would prevent amortizing the weights over many requests in batches...

Re: A recent experience with ChatGPT 5.5 Pro

#537

Post by jplusequalt »

brookst wrote: post #522
jplusequalt wrote: post #499

Earlier quoted context omitted.

>The map isn’t the territory; thinking about what to build is just as valid as thinking about how to build it If this was the case, the demand for architects would be different than what see today.

Not following. The demand for architects is gated by the cost of building. And the metaphor is that all if us who used to be carpenters can be architects, in the software sense. Maybe some people don’t want to be, but it is still a very thought-intensive profession.

The question is whether vibe coding requires a lot of thought, and I don't believe it does. The industry in in full blown idiocracy at the moment, and if you think you're a real engineer despite not understanding what you're building, you're a joke.

Re: A recent experience with ChatGPT 5.5 Pro

#538

Post by alexashka »

MinimalAction wrote: post #327
alexashka wrote: post #151

Earlier quoted context omitted.

> I always believed that my work speaks for itself and transcends beyond my limited time on this cosmic experience Any statement preceded by the word 'believe' is a coping mechanism. > This notion of immortality was just a small intangible bonus I hoped for when I jumped into grad school Any statement preceded by the word 'hope' is a coping mechanism. > AI is making me feel less worthy Worth comes from understanding,…

I strongly disagree on beliefs and hopes are coping mechanisms. Coping from what? Beliefs and hopes are what they are. But I agree worth should be derived from understanding, not through achievement.

> Coping from what?

From not having the thing you hope for or believe in.

I want a cookie.

I'm going to get a cookie. No believe, no hope.

I may not get a cookie. Oh no. I'm stressed. How do I deal with the stress? I hope I get a cookie. I believe I'm going to get a cookie. That's a coping mechanism.

Re: A recent experience with ChatGPT 5.5 Pro

#539

Post by hackable_sand »

elAhmo wrote: post #482
Jweb_Guru wrote: post #389

This jives with what I've experienced in the brief time I had access to 5.5 Pro. It's the very first LLM that I feel like I can wrangle into solving tedious, but straightforward, problems correctly. It still makes a ton of mistakes and needs to be very rigidly guided, but it does a pretty good job of tracing its own reasoning and correcting itself in a way that the other models do not. The downside (not noted in the…

> It's the very first LLM that I feel like I can wrangle into solving tedious, but straightforward, problems correctly. It still makes a ton of mistakes and needs to be very rigidly guided, but it does a pretty good job of tracing its own reasoning and correcting itself in a way that the other models do not. I swear that people have said the same thing with effectively every new model that came out in the last six mo…

They did. The scam continues.

Re: A recent experience with ChatGPT 5.5 Pro

#540

Post by hackable_sand »

sidkshatriya wrote: post #96
einrealist wrote: post #77

"After 16 minutes and 41 seconds, it came back" ... "further 47 minutes and 39 seconds" ... "After 13 minutes and 33 seconds" ... "After 9 minutes and 12 seconds" ... "After 31 minutes and 40 seconds" ... plus other computations Anyone spotting the issue here? What did that really cost? I am not against compute being used for scientific or other important problems. We did that before LLMs. However, the major LLM gate…

> "After 16 minutes and 41 seconds, it came back" ... "further 47 minutes and 39 seconds" ... "After 13 minutes and 33 seconds" ... "After 9 minutes and 12 seconds" ... "After 31 minutes and 40 seconds" ... plus other computations Anyone spotting the issue here? What did that really cost? Whatever the Joules... (convert to $ using your preferred benchmark price) it is a fraction to what it might take a human Ph. D. w…

Are you guys being intentionally obtuse?

Do you understand the difference between an apple and an apple tree?

Post reply on HN