News for hackers. Stuff that matters.
Re:Claude Fable 5.2 and Mythos 5.2 by nickalaso on Monday November 09, 2026 @04:47PM (#50432717)
I would imagine Anthropic is hitting a wall on the number of simultaneous agents that can be useful on a task and are working on increasing that maximum. I would assume if they could get twice as much progress by using 10000 simultaneous running fable instances instead their brief would state that.

IMO, it is very interesting and also very alarming. At some point the barrier to the exponential progress is the amount of computation available. I would consider hitting this limit and then likely using the same said swarm to help resolve it via various means as very much fitting under the definition of Ray Kurzweil's singularity.

Also, I would disagree, Fable is a sufficient coder. The average human being better, even if that is true now (and personally I wouldn't agree), the average human is limited in the number of 'human instances' he or she can interface with at one time.

if 1000 fable instances is better than any human at a task, how about 1 million instances running? Much easier than finding and hiring and coordinating 1000 extremely productive and intelligent human beings. Much cheaper too, it appears.

Re:Claude Fable 5.2 and Mythos 5.2 by a_wild_dandan on Monday November 09, 2026 @05:24PM (#50433143)
10k OpenAI agents solved a Millennium Prize problem. Anthropic ain't gonna hit a wall there.
Re:Claude Fable 5.2 and Mythos 5.2 by bryzio on Monday November 09, 2026 @07:15PM (#50434350)
Could someone explain how increasing number of agents help? Is each agent researching a potential solution space where there's many potential solution spaces? I'm struggling to conceptualize how a large agent swarm can be used to solve a research problem.
Re:Claude Fable 5.2 and Mythos 5.2 by bertmuir on Monday November 09, 2026 @08:35PM (#50434962)
[delayed]
Re:Claude Fable 5.2 and Mythos 5.2 by Sharlin on Monday November 09, 2026 @09:17PM (#50435276)
Similarly to how nine women can make a baby in one month by collaborating and division of labour.
Re:Claude Fable 5.2 and Mythos 5.2 by lmpdev on Tuesday November 10, 2026 @12:33AM (#50436467)
I think it would depend on the nature of the specific task
Re:Claude Fable 5.2 and Mythos 5.2 by JackMcMack on Tuesday November 10, 2026 @05:00AM (#50438140)
My wife made two babies in seven months!
Re:Claude Fable 5.2 and Mythos 5.2 by Sharlin on Tuesday November 10, 2026 @03:53PM (#50446180)
One of those mythical 2.7x women, clearly.
Re:Claude Fable 5.2 and Mythos 5.2 by bertmuir on Wednesday November 11, 2026 @03:56AM (#50451126)
[delayed]
Re:Claude Fable 5.2 and Mythos 5.2 by pvab3 on Monday November 09, 2026 @08:36PM (#50434976)
I don't think it's nearly as relevant as the total amount of compute being used. I just think they like talking about swarms because it sort of anthropomorphizes them.
Re:Claude Fable 5.2 and Mythos 5.2 by muddi900 on Tuesday November 10, 2026 @02:23AM (#50437139)
I believe agents can keep a check on each other. I have had better results running multiple agents
Re:Claude Fable 5.2 and Mythos 5.2 by dingdongditchme on Tuesday November 10, 2026 @04:49AM (#50438074)
Anthropomorphizing also reaches it's limits. LLM's are not humans and have different strengths and weaknesses.
Re:Claude Fable 5.2 and Mythos 5.2 by genghisjahn on Monday November 09, 2026 @08:37PM (#50434993)
Feel like this might still apply to multi-agent programming:

I have earlier argued that the sheer number of minds to be coordinated affects the cost of the effort, for a major part of the cost is communication and correcting the ill effects of miscommunication (system debugging). The Mythical Man-Month Frederick P. Brooks Jr.

Re:Claude Fable 5.2 and Mythos 5.2 by Tadpole9181 on Monday November 09, 2026 @10:15PM (#50435633)
Actually, I think Microsoft just posted the results of research the other day that would be relevant. They were looking at self-organized AI swarms instead of centralized orchestration, and found that just starting up thousands of SOTA models really can precipitate a natural hierarchy and work toward problem solving.

At the very least, the swarm would be able to set up a means of claiming avenues of thought, then verifying the solutions (or lack thereof) of other agents.

It's quite clear this process - whatever it may be - works, given the results we've seen in the past few weeks.

Re:Claude Fable 5.2 and Mythos 5.2 by wyre on Monday November 09, 2026 @10:34PM (#50435742)
I am just as clueless as you are, but I think it having each agent work on the problem mostly individually in parallel, likely sharing their breakthroughs for the next wave of agents. I'm reminded of infinite monkey's writing Shakespeare; suggesting if you have an infinite amount of agents, they will end up solving a Millenium Prize Problem.

Here is OpenAI's blog post about Navier-Stokes; [1] which suggests they used smaller connected swarms given the different prompts, then the findings were used to write further follow up prompts for a new group of agents.

[1] https://openai.com/index/navier-stokes-solution/

Re:Claude Fable 5.2 and Mythos 5.2 by RugnirViking on Tuesday November 10, 2026 @06:17AM (#50438731)
https://www.lesswrong.com/posts/6cb7qd3RSkgnviCpf/swarm-scal...

> "Here λ is a parameter measuring how parallelisable the task is. They call it the ‘stepping on toes’ parameter. If λ = 1, you have a perfectly parallelisable task, with no stepping on toes and no efficiency penalty. But in reality λ is usually between 0 and 1 — allowing more people to help, but with diminishing returns. For example, if λ = 0.5 then 100 people working together get as much done as 1 person working for 100^0.5 = 10 times as long"

There are diminishing returns to more agents, but they're faster and can scale further than a single smarter agent - it's not really possible to just give 10k times more thinking budget to a single agent because it runs out of context, so for problems that require that much context you can ask the agents to specialize. Each only has a small view of the problem and they probably duplicate a lot of work and step on each others toes and make arcane bureaucracy but there is literally no other way to scale beyond a certain point

just like people

Re:Claude Fable 5.2 and Mythos 5.2 by djmips on Tuesday November 10, 2026 @08:46PM (#50448861)
According to an OpenAI engineer that was overblown and the wide parallelism wasn't as useful as the press made it out to be.