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

GPT-5.6 Sol Ultra will be in Codex

twitter.com

Post reply on HN
Print view View original

121–130 of 433 posts

Re: GPT-5.6 Sol Ultra will be in Codex

#121

Post by tfehring »

gbnwl wrote: post #85
andai wrote: post #4

For 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.

How is this any different than what we have already? We've had this ability for ages (6+ months, decades in the AI world), you can literally today easily prompt CC or Codex to use subagents to accomplish tasks and they'll do it well. My entire workflow is one top level orchestrator chat creating tickets to dispatch to subagents to implement, and other subagents to verify. Why is this being sold as a new thing? Have H…

I assume this is ~equivalent to ultracode in Claude Code, which can deploy a tree of hundreds of nested subagents and was just released experimentally 5 weeks ago IIRC.

Re: GPT-5.6 Sol Ultra will be in Codex

#122

Post by nl »

cubefox wrote: post #111
nl wrote: post #58

Earlier quoted context omitted.

The source is the GPT 5.5 System Card: > We generally treat GPT-5.5’s safety results as strong proxies for GPT-5.5 Pro, which is the same underlying model using a setting that makes use of parallel test time compute. As noted below, we separately evaluate GPT-5.5 Pro in certain cases because we judge that the setting could materially impact the relevant risks or appropriate safeguards posture. https://deploymentsafet…

> makes use of parallel test time compute Any idea what that means exactly? I vaguely remember that ChatGPT Pro was originally called "deep thought", just like Geminis "deep thought" feature (or "deep think"?), so it seems likely they are using the same approach.

Their methodology isn't published.

Its widely accepted[1] that it runs the same query through the model in parallel and then has a model that either selects the best answer or synthesizes an answer from the multiple ones generated.

I believe most people think it runs 6 sub-models, but I think that is based on the pricing.

It's a pity that OpenAI doesn't publish details like this.

[1]eg https://news.ycombinator.com/item?id=48799977

Re: GPT-5.6 Sol Ultra will be in Codex

#123

Post by dannyw »

nl wrote: post #122
cubefox wrote: post #111

Earlier quoted context omitted.

> makes use of parallel test time compute Any idea what that means exactly? I vaguely remember that ChatGPT Pro was originally called "deep thought", just like Geminis "deep thought" feature (or "deep think"?), so it seems likely they are using the same approach.

Their methodology isn't published. Its widely accepted[1] that it runs the same query through the model in parallel and then has a model that either selects the best answer or synthesizes an answer from the multiple ones generated. I believe most people think it runs 6 sub-models, but I think that is based on the pricing. It's a pity that OpenAI doesn't publish details like this. [1]eg https://news.ycombinator.com/it…

Basically like passes@6 or passes@5 if you’re doing a benchmark, except for your real tasks.

Pro is quite limited on the web UI I reckon. This approach can be highly effective for reasonably verifiable task, for example, write comprehensive unit tests pointing out a tricky bug, get multiple agents to swarm at it.

Re: GPT-5.6 Sol Ultra will be in Codex

#124

Post by camillomiller »

solumunus wrote: post #114
throw394042 wrote: post #30

I'm working in large US corporation. And I see that I already have access to 5.6-Sol Ultra on my corporate account. I haven't really used it yet. 2 months ago management was showing us scoreboards, praising leaders who used most tokens. Last few weeks, we're getting weekly emails, telling us that whenever we can - we should use cheaper models, and that we should watch the page which shows our tokens usage.

> 2 months ago management was showing us scoreboards, praising leaders who used most tokens. Everyone is insane.

It‘s a collective psychosis. There is not other explanation.

Re: GPT-5.6 Sol Ultra will be in Codex

#126

Post by bulder »

dprkh wrote: post #116
throw394042 wrote: post #30

I'm working in large US corporation. And I see that I already have access to 5.6-Sol Ultra on my corporate account. I haven't really used it yet. 2 months ago management was showing us scoreboards, praising leaders who used most tokens. Last few weeks, we're getting weekly emails, telling us that whenever we can - we should use cheaper models, and that we should watch the page which shows our tokens usage.

Are corporate employees not allowed to use personal subscriptions?

Sounds like a bad idea in general. Any data use agreements get lost, shadow-IT brews and nobody knows what tools to use, oh and it's against the service terms.

Re: GPT-5.6 Sol Ultra will be in Codex

#128

Post by user_of_the_wek »

dlt713705 wrote: post #107
jaggederest wrote: post #68

Earlier quoted context omitted.

I feel like it's not crazy to run Javascript in the browser... We've come so far I almost forgot where it all started.

Per latest available data, point of origin traces back approximately 13.8 billion years to a singular event designated "Big Bang". YMMV

> In the beginning, the Universe was created. This had made many people very angry and has been widely regarded as a bad move.

Re: GPT-5.6 Sol Ultra will be in Codex

#130

Post by patentlyze »

andai wrote: post #4

For 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.

Pro also makes you ask it to use sub-agents instead of just doing it when useful.

Hopefully, 5.6 will automatically spawn sub-agents without needing to ask.

Post reply on HN