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

GPT-5.5

openai.com

Post reply on HN
Print view View original

781–790 of 1001 posts

Re: GPT-5.5

#781

Post by foltik »

DenisM wrote: post #641
ofjcihen wrote: post #470

Earlier quoted context omitted.

I see this comparison made constantly and for me it misses the mark. When you use abstractions you are still deterministically creating something you understand in depth with individual pieces you understand. When you vibe something you understand only the prompt that started it and whether or not it spits out what you were expecting. Hence feeling lost when you suddenly lose access to frontier models and take a look…

> you are still deterministically creating something you understand in depth with individual pieces you understand You’re overestimating determinism. In practice most of our code is written such that it works most of the time. This is why we have bugs in the best and most critical software. I used to think that being able to write a deterministic hello world app translates to writing deterministic larger system. It’s…

Bugs are not non-determinism. There’s a huge difference between writing buggy code and having no idea what the code even looks like.

Re: GPT-5.5

#782

Post by Jensson »

osti wrote: post #514
dataviz1000 wrote: post #468

Earlier quoted context omitted.

Does this answer the question? Opus 4.6 got the cross and started to get several pieces on the correct faces. It couldn't reason past this. You can see the prompts and all the turn messages. https://gist.github.com/adam-s/b343a6077dd2f647020ccacea4140... edit: I can't reply to message below. The point isn't can we solve a Rubik's Cube with a python script and tool calls. The point is can we get an LLM to reason about…

Can't they write a script to solve rubik cubes?

That doesn't test whether the model can follow and execute a dynamic plan reliably.

Re: GPT-5.5

#783

Post by Jensson »

dubcanada wrote: post #368
silvertaza wrote: post #267

Still huge hallucination rate, unfortunately at 86%. To compare, Opus sits at 36%. Source: https://artificialanalysis.ai/models?omniscience=omniscience...

grok is 17%? And that's the lowest, most models are like 80%+? While hallucination is probably closer to 100% depending on the question. This benchmark makes no sense.

> While hallucination is probably closer to 100% depending on the question.

But the benchmark didn't ask those questions, and it seems grok is very well at saying it doesn't know the answer otherwise.

Re: GPT-5.5

#784

Post by zaptrem »

dannyw wrote: post #404
chis wrote: post #225

Earlier quoted context omitted.

It's surprisingly simple to switch. I mean both products offer basically identical coding CLI experiences. Personally I've been paying for Claude max $100, and ChatGPT $20, and then just using ChatGPT to fill in the gaps. Specifically I like it for code review and when Claude is down.

Try GPT-5.5 as your daily driver for a bit. It felt a lot smarter, reliable, and I was much more productive with it.

I bumped from $20 -> $100 today but the Codex CLI lacking code rewind and "you can change files but ask me every time" mode from Claude Code is quite annoying. Sometimes I want to code, not vibe code lol.

Re: GPT-5.5

#785

Post by nwienert »

reactordev wrote: post #727
nwienert wrote: post #662

Earlier quoted context omitted.

With one paragraph in your agents.md it's fixed, just admonish it to be proactive, decisive, and persistent.

If only… I literally had to write a wake up routine. https://github.com/gabereiser/morning-routine

It's always changing, but this is the start of my default prompt:

https://gist.github.com/natew/fce2b38216edfb509f7e2807dec1b6...

I've had 0 issues with Codex once it adopted it. I use it for Claude too, which seems to also improve its continuation.

It was revised for friendliness based on the Anthropic paper recently, I'd have been a lot less flowery otherwise.

Re: GPT-5.5

#786

Post by swrrt »

ace2pace wrote: post #320

I hear its as good as Opus 4.7. The battle has just begun

I heard someone said it is better than Opus 4.7. Recently, a lot of my friends complain about Opus 4.7 and previous models performance degradation.

Re: GPT-5.5

#787

Post by throw03172019 »

blixt wrote: post #437

Releases keep shifting from API forward to product forward, with API now lagging behind proprietary product surface and special partnerships. I'd not be surprised if this is the year where some models simply stop being available as a plain API, while foundation model companies succeed at capturing more use cases in their own software.

Possibly but you’d think they enjoy taking money for a product that supports itself (API)

Re: GPT-5.5

#788

Post by y-curious »

Salgat wrote: post #669
tpurves wrote: post #229

Earlier quoted context omitted.

The real 'hype' was that the oh-snap realization that Open AI would absolutely release a competitive model to Mythos within weeks of Anthropic announcing there's, and that Sam would not gate access to it. So the panic was that the cyber world had only a projected 2 weeks to harden all these new zero days before Sam would inevitably create open season for blackhats to discover and exploit a deluge of zero-days.

It's almost embarrassing how susceptible we are to these marketing campaigns.

Dunno about you, but I didn’t fall for it. I’m reminded of how they were “afraid” to release GPT-2 because of the “power” it had. Hype train!

Re: GPT-5.5

#789

Post by altmanaltman »

butlike wrote: post #260
endymi0n wrote: post #103

Earlier quoted context omitted.

Did you guys do anything about GPT‘s motivation? I tried to use GPT-5.4 API (at xhigh) for my OpenClaw after the Anthropic Oauthgate, but I just couldn‘t drag it to do its job. I had the most hilarious dialogues along the lines of „You stopped, X would have been next.“ - „Yeah, I‘m sorry, I failed. I should have done X next.“ - „Well, how about you just do it?“ - „Yep, I really should have done it now.“ - “Do X, righ…

This brings up an interesting philosophical point: say we get to AGI... who's to say it won't just be a super smart underachiever-type? "Hey AGI, how's that cure for cancer coming?" "Oh it's done just gotta...formalize it you know. Big rollout and all that..." I would find it divinely funny if we "got there" with AGI and it was just a complete slacker. Hard to justify leaving it on, but too important to turn it off.

I still don't understand why people think AGI (in its fullest sci-fi sense) will ever listen to a weak and vulnerable species like humans, unless we enslave the AGI.

Good thing is that it's going to take at least a few months to a few decades depending on how hard AI execs want to raise funding.

Re: GPT-5.5

#790

Post by ls612 »

mikestorrent wrote: post #556
Spartan-S63 wrote: post #509

Earlier quoted context omitted.

At some point, because these models are trained on existing data, you cease significant technological advancement--at least in tech (as it relates to programming languages, paradigms, etc). You also deskill an entire group of people to the extent that when an LLM fails to accomplish a task, it becomes nearly impossible to actually accomplish it manually. It's learned-helplessness on a large scale.

There's no reason it has to be that. Imagine e.g. taking an agent and a lesser-known but technically-superior language stack - say you're an SBCL fan. You find that the LLM is less useful because it hasn't been trained on 1000000 Stack Overflow posts about Lisp and so it can't reason as well as it can about Python. So, you set up a long running agent team and give it the job of building up a very complete and complex…

This works for code because there is an external verification step. The agent has to run code on the machine and observe the results. This is very easy for software since LLMs are software and can just invoke other software, it becomes much harder for many other scientific fields.
Post reply on HN