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

GPT-5.6

openai.com

Post reply on HN
Print view View original

821–830 of 1001 posts

Re: GPT-5.6

#821

Post by Squarex »

gorgmah wrote: post #341

Just used terra ultra for exactly one prompt in codex and it ate through my full 5h window in about 10mns (20$ plan). The results look pretty good though. Luckily I have had my chatGPT subscription for a while and have a bunch of resets available (nice compared to anthropic). Assuming I take the 5x plan it would give me about an hour of active sessions with terra ultra (maybe ultra is not good value regarding tokens?…

Same for me, but it produced much better answer than what would I expect from GPT 5.5 xhigh. Also the good think about Codex is that it always finishes the prompt, even when the limit was reached in the half.

Re: GPT-5.6

#822

Post by zmmmmm »

inciampati wrote: post #118
eig wrote: post #38

Funny to see that they did not include Fable 5 in their GeneBench and LifeSciBench comparisons because "it does not answer advanced biology questions and refuses the majority of questions in this eval". Winner by default!

This is a major reason why I and a number of biologists I've talked to have canceled their anthropic accounts recently. Not working is not working.

Yes it has completely turned me around - was all in on Anthropic but now it just looks too risky. Better off leaning into open models. Even if I found a way to work with the restrictions as they are, who is to say they won't suddenly change tomorrow. It's not worth it.

Re: GPT-5.6

#823

Post by hk__2 »

nilkn wrote: post #181
hk__2 wrote: post #142

Earlier quoted context omitted.

I’d argue the opposite. I’ve switched back and forth from one to the other and Opus/Fable has been constantly better than any GPT in my daily work. It’s a bit slower but it does the things right, with as little code as possible, some comments where needed. Codex is faster but you always have to correct it because it got something wrong; it writes tons of code ("let me add a small helper") with obvious comments.

I'm not sure how meaningful this is. Fable only just recently become more broadly available, and GPT-5.6 is launching broadly today.

The comment I was responding to was talking about Codex usage in the past few months. This is a general feeling about Codex with Claude, not a model-to-model comparison.

Re: GPT-5.6

#824

Post by hagen8 »

Syntaf wrote: post #6

Ok long time Claude Code user here; lately I've started to realize there's other great models out there I should be trying, but I'm hesitant to leave Claude Code behind for something new. What's the consensus today on codex vs claude code, does it really matter anymore?

In my opinion Opus is waaayy better in agentic orchestration. It feels like it can natively deal with multiple subagents whereas gpt needs to be taught extensively.

Re: GPT-5.6

#825

Post by Kuinox »

maxnevermind wrote: post #643
meetpateltech wrote: post #154

GPT-5.6 Sol sets a new SOTA on ARC-AGI-3: 7.8% Sol is the first verified frontier model to ever beat an ARC-AGI-3 game https://arcprize.org/results/openai-gpt-5-6

I'm surprised it is that low. Are not all top AI labs "cheating" and workaround LLMs's low sample efficiency by hiring people to generate more data points - similar problems with answers, so they can train models on those and improve scores? A good benchmark for general intelligence probably should be a complete black box, no sample data given/leaked at all.

Oh it's because the bench is lying. You need to pass each level without failing, if you fail a level, it count as you "lost" the minigame. The fact it start to get a score means it managed to get a 100% score on one of the minigame.

Re: GPT-5.6

#826

Post by rldjbpin »

Jcampuzano2 wrote: post #152

I really wish there was just an easy guide on when to use Sol vs Terra vs Luna, and it just moves further into confusing territory when it comes to naming. The naming convention is especially difficult to decipher depending on what your native language is. Of course a latin language speaker might be able to easily determine oh yeah each one is slightly bigger than the other but I still think it borderlines too confus…

> I really wish there was just an easy guide on when to use Sol vs Terra vs Luna

Their dev guide has the following:

> Use gpt-5.6-sol for frontier capability, gpt-5.6-terra for a balance of intelligence and cost, or gpt-5.6-luna for efficient, high-volume workloads. The gpt-5.6 alias routes requests to gpt-5.6-sol

https://developers.openai.com/api/docs/guides/latest-model#u...

Re: GPT-5.6

#827

Post by rldjbpin »

simonw wrote: post #379

Here are 18 pelicans - six each for Luna, Terra and Sol at the six different reasoning effort levels (plus the price to generate each one): https://static.simonwillison.net/static/2026/gpt-5.6-pelican... Or if you want to see some in 3D, OpenAI featured a pelican riding a tricycle, bicycle, pony and another pelican in their livestream this morning: https://www.youtube.com/live/Wq45rvPGNHs?t=1070s

terra is just weird. in this nothingburger test, time nor higher costs seem to not strongly correlate with the aesthetics.

Re: GPT-5.6

#828

Post by steve-atx-7600 »

energy123 wrote: post #677
Jcampuzano2 wrote: post #152

I really wish there was just an easy guide on when to use Sol vs Terra vs Luna, and it just moves further into confusing territory when it comes to naming. The naming convention is especially difficult to decipher depending on what your native language is. Of course a latin language speaker might be able to easily determine oh yeah each one is slightly bigger than the other but I still think it borderlines too confus…

I use the strongest model (5.5 now 5.6 sol) on the highest reasoning effort with /fast for everything. With a $200 pro sub I can't even use my weekly limit. And it's faster than using a weaker model that makes more mistakes which I have to waste time fixing.

I used to have the same experience until 5.6 sol xhigh. I have instructions in my code review skill and agents.md to encourage parallelism including multiple agents as long as quality isn’t impacted. I additionally instruct codex to not use less capable agents because at least with 5.5 this would seriously increase slop. Maybe sol is smarter about delegation. Hopefully because I’ll have to slow down or hopefully get approval for extra use credits. Now’s a great time for a limit reset if anyone from open ai is reading :).

Re: GPT-5.6

#829

Post by XenophileJKO »

jrflo wrote: post #415
Jcampuzano2 wrote: post #152

I really wish there was just an easy guide on when to use Sol vs Terra vs Luna, and it just moves further into confusing territory when it comes to naming. The naming convention is especially difficult to decipher depending on what your native language is. Of course a latin language speaker might be able to easily determine oh yeah each one is slightly bigger than the other but I still think it borderlines too confus…

My guess is that it's the same for Haiku/Sonnet/Opus: Biggest model for architecture and high level planning and technically challenging problems, medium model for simple implementation tasks, small model is for nothing

small models are good for "finding stuff" and "summarizing" in support of the large models.

Re: GPT-5.6

#830

Post by davedx »

Syntaf wrote: post #6

Ok long time Claude Code user here; lately I've started to realize there's other great models out there I should be trying, but I'm hesitant to leave Claude Code behind for something new. What's the consensus today on codex vs claude code, does it really matter anymore?

I switch between both as my daily drivers.

I do almost all my regular coding tasks with Codex 5.5 on medium. Sometimes for niche edge cases, or when I run out of tokens on my Codex sub, I'll switch to Claude. Some recent examples where Claude was able to solve things Codex couldn't:

- 3D gamedev layout: I asked Codex to render a solar system in a certain camera positioning, saying it needed to fit the planets of the system to the viewport. Codex just couldn't do it, even on high reasoning: Claude Opus did it first attempt.

- Tricky Tiptap image drag-n-drop layout implementation: Codex failed this after numerous iterations. Claude Opus also struggled mightily to get it to work, but I think around 3 attempts it nailed it. Both of them ended up grepping the Tiptap code from node_modules - that's the kind of task it was.

But these are really isolated examples. Across all my projects (I have many; mostly TypeScript, but also things like C#), Codex "Just Works" (tm), with minimal prompting effort from me.

Post reply on HN