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

GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

twitter.com

Post reply on HN
Print view View original

51–60 of 219 posts

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#51

Post by deadlast2 »

jychang wrote: post #30
aarvin_roshin wrote: post #4

Thoughts[^0] from Theo, who had early access: > It's a damn good model. Not quite as "smart" as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5. > It is incredibly determined. Will run for a day without even using a /goal. It understands subagents incredibly well and is great at orchestrating. It's super pleasant in use cases like OpenClaw and Hermes Agent. It knows iOS dev incredibly w…

> Not quite as "smart" as Fable, but it is incredibly capable. THIS IS BECAUSE GPT-5.6 SOL IS... just a more posttrained version of GPT-5.5, not a brand new bigger model than GPT-5.5. It's not like how Mythos is bigger than Opus. OpenAI switching to Sol/Terra/Luna renaming is just a way to rip off people and charge more usage for the same sized model. GPT-5.6 --------> GPT-5.6 Sol GPT-5.6-mini ---> GPT-5.6 Terra GPT-…

I use Open AI and Claude a lot right like a lot everyday for hours multiple hours. Open AI gives much more value for money than Claude much more I'd say x 10. Mainly I use it for writing fiction books and literally Claude is locked 90% of everyday trying to jip me for tokens. It's not as good at coding for what I do which is a very complicated application. However it is very good at writing it's really good which is why I keep it right but over 90% maybe actually all of my work except the initial draft of a chapter is done by open AI.

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#52

Post by bottlepalm »

Coding with AI it feels like if you're not using the best model then you're possibly missing out - creating less capable, maintainable, just plain 'good' code. Why waste time using anything less than the best and cleaning up the mess later on. This is why I feel like local models and Chinese models aren't taking off (and Gemini/Grok) - they work, but they're plain just not as good as OpenAI/Anthropic. If you have the money then it doesn't make sense to code with anything else.

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#53

Post by reassess_blind »

tyteen4a03 wrote: post #46
reassess_blind wrote: post #6

I’m bouncing back between Codex and Claude like a ping-pong ball. I much prefer the experience using Codex, less verbose and to-the-point I’ve found. But Fable, being as strong as it is, is a big draw for Claude right now. I’ll likely switch back to Codex if 5.6 Sol is comparable.

Why not both? T3 Code exists.

Hadn't heard about it. Launching either "codex" or "claude" from cli isn't exactly a pain point I was looking to fix.

Edit: I guess the real answer is that I don't want multiple subscriptions. I use one for a month, and then decide if I switch to the other.

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#54

Post by throwuxiytayq »

tedsanders wrote: post #50
prodigycorp wrote: post #32

Earlier quoted context omitted.

Do you have a source for this? I'm pretty sure responses api is only there to obfuscate reasoning, but that they're still keeping reasoning traces in the backend.

I work at OpenAI and can confirm that's correct: reasoning tokens are discarded after each new user turn (though not after each message or tool call). Our docs show a diagram here: https://developers.openai.com/api/docs/guides/reasoning > Input and output tokens from each step are carried over, while reasoning tokens are discarded. Keeping reasoning tokens around is better for caching and for remembering past insight…

dude what the hell

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#55

Post by behnamoh »

jychang wrote: post #30
aarvin_roshin wrote: post #4

Thoughts[^0] from Theo, who had early access: > It's a damn good model. Not quite as "smart" as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5. > It is incredibly determined. Will run for a day without even using a /goal. It understands subagents incredibly well and is great at orchestrating. It's super pleasant in use cases like OpenClaw and Hermes Agent. It knows iOS dev incredibly w…

> Not quite as "smart" as Fable, but it is incredibly capable. THIS IS BECAUSE GPT-5.6 SOL IS... just a more posttrained version of GPT-5.5, not a brand new bigger model than GPT-5.5. It's not like how Mythos is bigger than Opus. OpenAI switching to Sol/Terra/Luna renaming is just a way to rip off people and charge more usage for the same sized model. GPT-5.6 --------> GPT-5.6 Sol GPT-5.6-mini ---> GPT-5.6 Terra GPT-…

OpenAI already has a Mythos level model, it's called GPTCyber and before that, it was called gpt-5.5-pro.

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#56

Post by nberkman »

bredren wrote: post #44
avereveard wrote: post #31

Earlier quoted context omitted.

Same. For some reason late opus model are very superficial doing ux work and so am using gpt for that, but backend is much better engineered by claude, gpt prefer to duplicate everything it needs on the spot causing class sprawl

How are y'all carrying context history from one agent to the other? I also flip between the models due to quota, TUI enhancements, model updates and service availability. To handle this, I built a thing that normalizes your transcripts between Claude Code and Codex into a shared DB, then a CLI and skill. It has made it so it doesn't matter what I built where (or when) I just refer to the work and drop in a /total-rec…

Sounds similar to the tool I built: https://github.com/neilberkman/ccrider#ccrider (although it's OSS whereas yours appears to be commercial)

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#57

Post by behnamoh »

reassess_blind wrote: post #6

I’m bouncing back between Codex and Claude like a ping-pong ball. I much prefer the experience using Codex, less verbose and to-the-point I’ve found. But Fable, being as strong as it is, is a big draw for Claude right now. I’ll likely switch back to Codex if 5.6 Sol is comparable.

How? I'm pretty much locked into Claude Code and even if gpt models are good now, the experience with codex CLI has been so bad I won't go back to it.

e.g., it still doesn't have /revise or /undo!

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#58

Post by simianwords »

Earlier I predicted that Fable and Sol would be of similar capability, I think I will be wrong. Here is why: there is no indication that there are any classifiers like in Fable. I think OpenAI found out how to lobotomise the model without classifiers but the tradeoff is that it is a weaker model. I wonder how people feel about that. Would you like a highly intelligent jagged model with classifiers or slightly less intelligent smooth model without classifiers?

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#59

Post by TheCoreh »

bottlepalm wrote: post #52

Coding with AI it feels like if you're not using the best model then you're possibly missing out - creating less capable, maintainable, just plain 'good' code. Why waste time using anything less than the best and cleaning up the mess later on. This is why I feel like local models and Chinese models aren't taking off (and Gemini/Grok) - they work, but they're plain just not as good as OpenAI/Anthropic. If you have the…

There are diminishing returns, especially for more mundane tasks. Fable is nice, and I bet Sol is also nice. But there really isn't much of a difference right now when using something beyond Opus or presumably Terra for most things. They're most useful when doing greenfield, highly complex/novel tasks. When Open Source catches up, it will be more widely adopted.

Re: GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

#60

Post by Philip-J-Fry »

bottlepalm wrote: post #52

Coding with AI it feels like if you're not using the best model then you're possibly missing out - creating less capable, maintainable, just plain 'good' code. Why waste time using anything less than the best and cleaning up the mess later on. This is why I feel like local models and Chinese models aren't taking off (and Gemini/Grok) - they work, but they're plain just not as good as OpenAI/Anthropic. If you have the…

That depends entirely on how you're using AI. If you're getting it to do all the hard thinking, then sure using the best model is probably always going to be better. But it's also going to be expensive.

Using cheaper models and using your skills and expertise from the pre-AI era can get you working just as fast. You've gotta be more specific about the work you need doing. It's less "vibes" based, but they're still effective.

Also, Chinese models absolutely are taking off. I used Claude and GPT at work, and then I tried using some Chinese models for personal projects. I am 100% convinced they're like 90% as good for 10% of the cost. But you've basically gotta be a good developer first and know what you want and know when it's giving you shit.

Post reply on HN