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

991–1000 of 1001 posts

Re: GPT-5.5

#991

Post by hx8 »

NoveltyEngine wrote: post #963
hx8 wrote: post #762

Earlier quoted context omitted.

I use Open Code as my harness. It's open source, bring your own API Key or OAuth token or self-hosted model. I've jumped from Opus 4.6 to Opus 4.7 to GPT 5.5 in the last 7 days. No big deal, intelligence is just a commodity in 2026. The actual harness is great, very hackable, very extendable.

Does Anthropic not actively ban people using oauth tokens in non-claude-code harnesses?

Yeah, for direct to Claude you need an API key. You can use other subscriptions like GitHub Copilot that expose Claude, but that path has been blocked.

Re: GPT-5.5

#992

Post by salad-tycoon »

jwr wrote: post #850
concinds wrote: post #380

Earlier quoted context omitted.

> Never thought I'd say this but OpenAI is the 'open' option again. Compared to Anthropic, they always have been. Anthropic has never released any open models. Never released Claude Code's source, willingly (unlike Codex). Never released their tokenizer.

What's "open" about any of these companies? I'm tired of words being misused. We have hoverboards that do not hover, self-driving cars that do not, actually, self-drive, starships that will never fly to the stars, and "open"… I can't even describe what it's used for, except everybody wants to call themselves "open".

It’s open as in the sign in the door of your favorite local diner that says;

“Yes, we are OPEN ”

Open, as in not currently out of business.

Re: GPT-5.5

#993

Post by deflator »

Got invited to try this, but it was too expensive. I gave it two tasks that I would expect Codex 5.3 xhigh to take $1-2 of tokens on. It used $20 on each, and one was on medium with the other on xhigh!

Re: GPT-5.5

#994

Post by snthpy »

nkohari wrote: post #924
snthpy wrote: post #828

Earlier quoted context omitted.

Does that mean that we're likely to see Mythos released soon?

The prevailing theory is that Anthropic doesn't have sufficient compute capacity to support Mythos at scale, which is the real reason it hasn't released.

Thanks. Makes sense

Re: GPT-5.5

#995

Post by anikom15 »

hapticmonkey wrote: post #507
davmar wrote: post #502

Earlier quoted context omitted.

i wonder if this is how engineers felt when the first electronic calculators came out and engineers stopped doing math by hand. did we feel uneasy that a new generation of builders didn't have to solve equations by hand because a calculator could do them? i'm not sure it's the same analogy but in some ways it holds.

The analogy would hold if there were 2 or 3 calculator companies and all your calculations had to be sent to them. If local models get good enough, I think it’s a very different scenario than engineers all over the world relying on central entities which have their own motives.

I think calculator is the wrong analogy. Go further back before even mainframes, when their were just a handful of purpose-built computers.

Re: GPT-5.5

#996

Post by stonecauldron »

an0malous wrote: post #86
sosodev wrote: post #66

I hope the industry starts competing more on highest scores with lowest tokens like this. It's a win for everybody. It means the model is more intelligent, is more efficient to inference, and costs less for the end user. So much bench-maxxing is just giving the model a ton of tokens so it can inefficiently explore the solution space.

The premise of the trillion dollars in AI investments is not that it’ll be as good as it currently is but cheaper. It’s AGI or bust at this point.

Right, but my belief is that the LLM paradigm is a dead end for AGI. We need something different to cross that barrier.

Re: GPT-5.5

#997

Post by stonecauldron »

pants2 wrote: post #293

Labs still aren't publishing ARC-AGI-3 scores, even though it's been out for some time. Is it because the numbers are too embarrassing?

Because they want to keep the narrative that they'll achieve AGI with LLMs alive.

Re: GPT-5.5

#998

Post by some-guy »

i_love_retros wrote: post #539
some-guy wrote: post #420

Earlier quoted context omitted.

I disagree. The amount of slop I need to code review has only increased, and the quality of the models doesn’t seem to be helping. It still takes a good engineer to filter out what is slop and what isn’t. Ultimately that human problem will still require somebody to say no.

Is anyone really reviewing code anymore though? It sounds like you are, but where I work its pretty much just scan the PR as a symbolic gesture and then hit approve. There's too much to review, to frequently.

I'm in a large enterprise context--you have to use human reviewers if you don't want to end up like Github's status page. So much context exists outside of the code that the bots are either not provided or are far too large of contexts for current windows.

Re: GPT-5.5

#999

Post by liamwire »

nubg wrote: post #581
pzo wrote: post #181

Earlier quoted context omitted.

On top of that I noticed just right now after updating macos dekstop codex app, I got again by default set speed to 'fast' ('about 1.5x faster with increased plan usage'). They really want you to burn more tokens.

wow wait so it wasn't just me leaving it on from an old session? sounds like criminal fraud to me tbh

Dark pattern is the term you're (incorrectly) describing.

Re: GPT-5.5

#1000

Post by cutler »

subhobroto wrote: post #729
cutler wrote: post #653

Earlier quoted context omitted.

Maybe people will finally take Marx seriously.

A lot of people already did. All their children and descendants now are staunch capitalists because they saw first hand the horrors of communism. I am from India and have friends who are immigrants from Russia, China and Cuba. We don't take lightly to being lectured about communism. We didn't move to the U.S., the bastion of capitalism, because communism had worked well for our grandfathers and parents and continues…

[dead]
Post reply on HN