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

Post by avereveard » Wed, Jul 08, 2026, 6:11 AM UTC

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.

Post by wahnfrieden » Wed, Jul 08, 2026, 6:17 AM UTC

prodigycorp wrote: post #32

CjHuber wrote: post #8

Earlier quoted context omitted.

Interesting to hear people like gpt-5.5. For me it feels smart only at one shot prompts, but if you try to build up session context before doing something it feels magnitudes inferior to Claude. I'm almost sure its because the thinking of previous turns is stripped with the responses API, so if I tell it to analyse something deeply, what remains of the understanding in future turns is only the short response text of…

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.

Post by oefrha » Wed, Jul 08, 2026, 6:23 AM UTC

stingraycharles wrote: post #22

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…

“Understands intent well and hammers until it gets there. “ If there’s anything I learned over the past 12-18 months is that this is a recipe for disaster, except for throwaway stuff. I thought most senior engineers settled on the fact that steering a model yields much better results?

Post by icepush » Wed, Jul 08, 2026, 6:25 AM UTC

stingraycharles wrote: post #22

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…

“Understands intent well and hammers until it gets there. “ If there’s anything I learned over the past 12-18 months is that this is a recipe for disaster, except for throwaway stuff. I thought most senior engineers settled on the fact that steering a model yields much better results?

Post by ttoinou » Wed, Jul 08, 2026, 6:28 AM UTC

bashtoni wrote: post #17

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…

I feel like listening to Theo about anything technical is like consulting a Labrador retriever for advice on quantum physics. Every time I've ever seen one of his videos it's pretty clear he has very little understanding of development or engineering. I first became aware of him from his early "unit tests are a waste of time" stuff, and it seems his skillset is building a personal brand. Fair play, he's clearly talen…