My notes on Anthropic's substantial essay about how they built their multi-agent research system, which has finally talked me around to taking multi-agent LLM prompt engineering seriously simonwillison.net/2025/Jun/14/...
Anthropic: How we built our multi-agent research system
OK, I'm sold on multi-agent LLM systems now. I've been pretty skeptical of these until recently: why make your life more complicated by running multiple different prompts in parallel when …
simonwillison.net
June 14, 2025 at 10:03 PM
My notes on Anthropic's substantial essay about how they built their multi-agent research system, which has finally talked me around to taking multi-agent LLM prompt engineering seriously simonwillison.net/2025/Jun/14/...
High-speed car chase involving federal agent ended with multi-car crash at Nina’s in St. Paul.
High-speed car chase involving federal agent ended with multi-car crash at Nina’s in St. Paul • Minnesota Reformer
A high-speed car chase that witnesses said involved a young man and a federal agent on Wednesday ended with a multi-car crash outside Nina’s Coffee Cafe in St. Paul. The man was transported away from ...
minnesotareformer.com
February 11, 2026 at 6:43 PM
High-speed car chase involving federal agent ended with multi-car crash at Nina’s in St. Paul.
A high-speed car chase involving a federal agent in St. Paul ended with a multi-vehicle crash and injuries to the fleeing driver, who was taken away in an ambulance. bit.ly/4kvJo0M
📸: Leila Navidi
📸: Leila Navidi
February 11, 2026 at 7:38 PM
A high-speed car chase involving a federal agent in St. Paul ended with a multi-vehicle crash and injuries to the fleeing driver, who was taken away in an ambulance. bit.ly/4kvJo0M
📸: Leila Navidi
📸: Leila Navidi
let's talk about "agents" (in the LLM sense). there's a lot of buzz around "multi-agent" systems where agents collaborate but... i don't really get how it differs from a thinking of a single agent with multiple modes of operation. what are the benefits of modeling as multi-agent?
November 23, 2024 at 12:00 AM
let's talk about "agents" (in the LLM sense). there's a lot of buzz around "multi-agent" systems where agents collaborate but... i don't really get how it differs from a thinking of a single agent with multiple modes of operation. what are the benefits of modeling as multi-agent?
Lets get the multi-agent learning community started up here: go.bsky.app/9gsefkW
November 13, 2024 at 10:45 PM
Lets get the multi-agent learning community started up here: go.bsky.app/9gsefkW
Congress is not powerless. Democrats must unify around an actual agenda.
1. Vote no on DHS funding bill.
2. Repeal the multi-year $75 billion funding for ICE.
3. End qualified immunity for ICE agents.
4. Investigate and prosecute every single ICE agent who broke the law.
1. Vote no on DHS funding bill.
2. Repeal the multi-year $75 billion funding for ICE.
3. End qualified immunity for ICE agents.
4. Investigate and prosecute every single ICE agent who broke the law.
January 25, 2026 at 2:36 PM
Congress is not powerless. Democrats must unify around an actual agenda.
1. Vote no on DHS funding bill.
2. Repeal the multi-year $75 billion funding for ICE.
3. End qualified immunity for ICE agents.
4. Investigate and prosecute every single ICE agent who broke the law.
1. Vote no on DHS funding bill.
2. Repeal the multi-year $75 billion funding for ICE.
3. End qualified immunity for ICE agents.
4. Investigate and prosecute every single ICE agent who broke the law.
We can simulate fish schools or ants in ways that solve complex problems (gradient detection, bridge building, nest selection) but no one would create this weird soul/no-soul dichotomy to argue they these that multi-agent swarms of extremely simple rules are “thinking”.
Once you’ve conceded that there’s nothing magic about humans or “living beings” that makes them the only entities allowed to think, it’s really hard to figure out an intellectually honest dividing line where the entities that are exercising creativity and solving complex problems aren’t thinking
September 20, 2026 at 4:48 PM
We can simulate fish schools or ants in ways that solve complex problems (gradient detection, bridge building, nest selection) but no one would create this weird soul/no-soul dichotomy to argue they these that multi-agent swarms of extremely simple rules are “thinking”.
hot (?) take: “multi-agent” is not a useful abstraction.
agents? sure
multiple copies of same agent executing in parallel? why not
“multi agent” will turn out to be a mirage like explainable AI
agents? sure
multiple copies of same agent executing in parallel? why not
“multi agent” will turn out to be a mirage like explainable AI
December 3, 2024 at 4:16 PM
hot (?) take: “multi-agent” is not a useful abstraction.
agents? sure
multiple copies of same agent executing in parallel? why not
“multi agent” will turn out to be a mirage like explainable AI
agents? sure
multiple copies of same agent executing in parallel? why not
“multi agent” will turn out to be a mirage like explainable AI
You should be embarrassed to write "multi-agent claudeswarms"
January 25, 2026 at 10:46 PM
You should be embarrassed to write "multi-agent claudeswarms"
“What’s your message to Kevin O’Leary if he still thinks you’re Chinese spies?”
🔥Jackie & Gabi of @elevateutahpac.bsky.social : “The only foreign agent here is a horrible Canadian multi-millionaire trying to ruin the environment in our country.”
Full: www.facebook.com/TheTNHoller/...
🔥Jackie & Gabi of @elevateutahpac.bsky.social : “The only foreign agent here is a horrible Canadian multi-millionaire trying to ruin the environment in our country.”
Full: www.facebook.com/TheTNHoller/...
May 17, 2026 at 4:30 AM
“What’s your message to Kevin O’Leary if he still thinks you’re Chinese spies?”
🔥Jackie & Gabi of @elevateutahpac.bsky.social : “The only foreign agent here is a horrible Canadian multi-millionaire trying to ruin the environment in our country.”
Full: www.facebook.com/TheTNHoller/...
🔥Jackie & Gabi of @elevateutahpac.bsky.social : “The only foreign agent here is a horrible Canadian multi-millionaire trying to ruin the environment in our country.”
Full: www.facebook.com/TheTNHoller/...
Meanwhile,
GitHub - openai/swarm: Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team. - openai/swarm
github.com
August 27, 2026 at 2:40 AM
Meanwhile,
MAORL (Multi-Agent Olof RL)
arxiv.org/abs/2512.16705
arxiv.org/abs/2512.16705
December 24, 2025 at 7:21 AM
MAORL (Multi-Agent Olof RL)
arxiv.org/abs/2512.16705
arxiv.org/abs/2512.16705
Check out how to use multi-agent workflows in VS Code! 💙
youtu.be/J5KTpq7hVn4?...
youtu.be/J5KTpq7hVn4?...
Multi-agent workflows in VS Code
YouTube video by Visual Studio Code
youtu.be
March 18, 2026 at 5:48 PM
Check out how to use multi-agent workflows in VS Code! 💙
youtu.be/J5KTpq7hVn4?...
youtu.be/J5KTpq7hVn4?...
April 19, 2026 at 2:44 AM
Bro, how are you not putting multi-agent claudeswarms in charge of your life!!! What’s wrong with you bro!!!
The AI evangelists want us all to conveniently forget that they were all telling us we had to buy bored apes or we would be left out of the Economy Of The Future four years ago.
January 25, 2026 at 5:56 PM
Bro, how are you not putting multi-agent claudeswarms in charge of your life!!! What’s wrong with you bro!!!
I have a draft of my introduction to cooperative multi-agent reinforcement learning on arxiv. Check it out and let me know any feedback you have. The plan is to polish and extend the material into a more comprehensive text with Frans Oliehoek.
arxiv.org/abs/2405.06161
arxiv.org/abs/2405.06161
A First Introduction to Cooperative Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized ...
arxiv.org
January 7, 2025 at 4:25 PM
I have a draft of my introduction to cooperative multi-agent reinforcement learning on arxiv. Check it out and let me know any feedback you have. The plan is to polish and extend the material into a more comprehensive text with Frans Oliehoek.
arxiv.org/abs/2405.06161
arxiv.org/abs/2405.06161
If Train Dreams ended in 2026 instead of 1968, it would close on a scene of Robert asking a custom AI agent for a multi-pillar structured analysis so he'd know which badass 3-leg Kalshi Combo parlay to bet on instead of all of that beautiful "connected to all of the world at once" airplane bullshit.
September 24, 2026 at 1:03 AM
If Train Dreams ended in 2026 instead of 1968, it would close on a scene of Robert asking a custom AI agent for a multi-pillar structured analysis so he'd know which badass 3-leg Kalshi Combo parlay to bet on instead of all of that beautiful "connected to all of the world at once" airplane bullshit.
oh nooooooooooooooooooooo www.bbc.co.uk/news/article...
Bill Oddie: The Goodies and Springwatch star dies at 85
His agent pays tribute to the "multi-talented" broadcaster, comedian and conservationist.
www.bbc.co.uk
July 27, 2026 at 9:39 AM
oh nooooooooooooooooooooo www.bbc.co.uk/news/article...
METR and Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
August 26, 2026 at 8:58 PM
METR and Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
Next GLM has a multi-agent focus maybe?
August 14, 2026 at 1:22 AM
Next GLM has a multi-agent focus maybe?
Stories I like:
Building Multi-Agent Workflows in C# with Microsoft Agent Framework
Building Multi-Agent Workflows in C# with Microsoft Agent Framework
Building Multi-Agent Workflows in C# with Microsoft Agent Framework
Mike explains that Microsoft Agent Framework goes beyond single agents by providing orchestration patterns for building multi-agent systems. Using examples, he shows how to compose specialized agen...
www.codemag.com
September 23, 2026 at 3:31 PM
Stories I like:
Building Multi-Agent Workflows in C# with Microsoft Agent Framework
Building Multi-Agent Workflows in C# with Microsoft Agent Framework