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.

▲ changoplatanero 6 hours ago | parent | next [-]

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.

▲

dools 6 hours ago | parent | next [-]

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.

▲

bombcar 5 hours ago | parent [-]

I really suspect that the models are basically the same below, it’s all in the prompt. The way I use them, surgically, they seem to perform about the same. Fable certainly hasn’t blow my socks off.

▲

X-Istence 4 hours ago | parent | next [-]

Where fable has blown me away is converting entire code bases and or refactoring across many different segments.

It’s far more careful than opus and puts far more effort into testing and validating by default.

Switching back to opus at work was a downgrade. Similar requests felt more clunky and needed far more hand holding.

	▲	bombcar 3 hours ago \| parent [-]
		Some of it feels boiled down to "opus works better when told not to be dumb, fable's prompt tells it not to be dumb." If they know much of what the tool is used for, they can customize prompts to "do that usage right" even if the user doesn't know exactly how to ask for it.

▲

bdcravens 3 hours ago | parent | prev | next [-]

This is where I think you see the distinction between two classes of LLM users:

1. Managers: those who generally know what needs to be done, and want it done faster, so they provide a lot of instructions and context (where many developers fall)

2. Executives: those who vaguely know the end goal, but are clueless about the process, and are willing to burn resources and cycles on a black box to get the result

▲

giancarlostoro 5 hours ago | parent | prev | next [-]

> Fable certainly hasn’t blow my socks off.

Same. I suspect they'll get better at taking in terrible prompts over time though... Maybe that's what Fable does better, reminds me of Sora 2, it would take my crappy prompt and expound upon it. I told it once to generate a video of someone working at some company that changed its name, but the old name had historic relevance, it referred to the new company name without me telling it to, by virtue of me wanting a video of TODAY with a 90s icon.

▲

anjel 4 hours ago | parent | prev [-]

> Fable certainly hasn’t blow my socks off. Same. Its not so much perf increase as cost increase justified by ambiguous perf increase.

▲

thomasahle 5 hours ago | parent | prev [-]

Do you have a source for this, or just rumors?

The responses I get from pro don't feel like ensembles. They are often very one directional.

▲

changoplatanero 5 hours ago | parent | next [-]

This can be because the summary model just picked the output from one of the sub agents.

▲

wahnfrieden 5 hours ago | parent | prev [-]

oops

▲

nl 4 hours ago | parent [-]

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://deploymentsafety.openai.com/gpt-5-5/model-data-and-t...

There have been multiple podcasts with people from OpenAI which have confirmed this.

▲

cubefox 2 hours ago | parent [-]

> 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.

▲

nl 2 hours ago | parent [-]

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

▲

dannyw 2 hours ago | parent [-]

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.

	▲	nl 2 hours ago \| parent [-]
		It's been very successful at frontier math tasks - a bunch of the Erdos questions have been solved by it - more than any other model. https://www.erdosproblems.com/

▲ ludamad 6 hours ago | parent | prev | next [-]

I imagine this is something like Anthropic's dynamic workflows where a JS file is created to make a little AI harness on the spot

▲ andai 4 hours ago | parent [-]

Wow, I hadn't heard of this!

  const audits = await pipeline(found.files, file =>
    agent(`Audit ${file} for missing authentication checks.`, { label: file }),
  )

I asked Claude in the browser if it could do anything like that. It wrote a little frontend app that calls the Anthropic API (with fetch()), without including a key. I expected that to fail, but it worked!

Apparently in the web chat (and also in Claude Code?[0] Though I haven't tried yet) they can call the Anthropic API and your subscription key gets auto-magicked into the requests somehow.

Those are two separate things of course (aside from the key-injection) but I guess there's no reason it couldn't run completely in the front-end... hmm...

[0] https://code.claude.com/docs/en/workflows

▲

jaggederest 4 hours ago | parent [-]

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.

▲

dlt713705 3 hours ago | parent [-]

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

	▲	user_of_the_wek 2 hours ago \| parent [-]
		> In the beginning, the Universe was created. This had made many people very angry and has been widely regarded as a bad move.

▲ gbnwl 3 hours ago | parent | prev | next [-]

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 HN users never tried tried asking CC or Codex to use subagents?

	▲	UnfitFootprint 3 hours ago \| parent \| next [-]
		The top comment on the thread explains this will involve subagent to subagent comms. To what effect I don’t know… I thought subagents were useful because they were explicitly single purpose and bound to a narrow context
	▲	tfehring 2 hours ago \| parent \| prev \| next [-]
		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.
	▲	ai_fry_ur_brain 3 hours ago \| parent \| prev [-]
		Because most people need complexity to be wrapped in a simple UI/UX. Most people just want the one-two button press and be on their way.

▲ patentlyze 2 hours ago | parent | prev | next [-]

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.

▲ ilsubyeega 4 hours ago | parent | prev [-]

i would believe this will be matched with something like orchestrator-focused model: https://news.ycombinator.com/item?id=48624782