Related:
Previewing GPT‑5.6 Sol: a next-generation model
GPT-5.6 Sol Ultra will be in Codex
11–20 of 433 posts
Re: GPT-5.6 Sol Ultra will be in Codex
#12Earlier quoted context omitted.
Maybe cache similar answers from others. Surprised if this is not already being done.
Like google search, this does not work because of how common long tail use is. What you think could be a big chunk, is more likely to be a fraction of a percent of queries. And what use is similar query caching - so you (very often! if actually cost effective, maybe half the time) get a response to a query that was different from yours. Including for when you have a lot of context input already. You’re going to get t…
Please pardon the pure speculation incoming. Yes, caching the answer doesn't seem useful. Caching the progression, the graph, may be. This is similar to making code changes with ed(1) instead of editing in vi.
The transform script(s) are cached and can be played back or adjusted. Surely for some breadth of question inputs, they map more often to similar answers--but not static answers; instead, evented edits.
It's nearly untenable for a human to keep private edit scripts to generate code changes. The extra steps for custom regex, essentially one-offs for a shared codebase, is inefficient. But maybe not to an LLM.
Re: GPT-5.6 Sol Ultra will be in Codex
#13For context: > Additionally, we’re introducing a new ultra mode that goes beyond the capabilities of a single agent by leveraging subagents to accelerate complex work. https://openai.com/index/previewing-gpt-5-6-sol/ Can someone explain how this compares with Pro? I thought Pro was already something similar.
For pro mode the agents worked independently and only when they all finished did a new agent take a look at everything to merge the work into a single response. The new thing involves subagents that have been trained to cooperatively pursue a task and are allowed to communicate with each other along the way.
Re: GPT-5.6 Sol Ultra will be in Codex
#14I still don't know why OpenAI doesn't put gpt-5.5-pro in Codex. It's one hell of a model and easily parallels Fable/Mythos. Sure, it'll use up your quota much faster but that's the price some users are willing to pay for absolutely high quality responses.
I think gpt-5.5-pro runs 12x parallel gpt-5.5 agents behind the scene and uses OpenAI's secret sauce to synthesize their answers into one insanely good response.
Re: GPT-5.6 Sol Ultra will be in Codex
#15Will individual subscribers have access?
I would assume yes - their goal is to capture consumer subscribers. Claude are going to take Fable away, and they're going to swoop in and give it to us.
Re: GPT-5.6 Sol Ultra will be in Codex
#16No Twitter, what’s he responding to?
Re: GPT-5.6 Sol Ultra will be in Codex
#17For context: > Additionally, we’re introducing a new ultra mode that goes beyond the capabilities of a single agent by leveraging subagents to accelerate complex work. https://openai.com/index/previewing-gpt-5-6-sol/ Can someone explain how this compares with Pro? I thought Pro was already something similar.
For pro mode the agents worked independently and only when they all finished did a new agent take a look at everything to merge the work into a single response. The new thing involves subagents that have been trained to cooperatively pursue a task and are allowed to communicate with each other along the way.
I tried a pro model out the other day and thought there must have been a bug in Pi’s cost calculations. But no, it’s absolutely fucking insane. Wasn’t even any better at the task.
Re: GPT-5.6 Sol Ultra will be in Codex
#18Earlier quoted context omitted.
Maybe cache similar answers from others. Surprised if this is not already being done.
Like google search, this does not work because of how common long tail use is. What you think could be a big chunk, is more likely to be a fraction of a percent of queries. And what use is similar query caching - so you (very often! if actually cost effective, maybe half the time) get a response to a query that was different from yours. Including for when you have a lot of context input already. You’re going to get t…
I would be very surprised if they hadn’t sorted out some form of shared KV caching
Re: GPT-5.6 Sol Ultra will be in Codex
#19Re: GPT-5.6 Sol Ultra will be in Codex
#20The full conversation https://xcancel.com/haider1/status/2073695124220006575#m