Search
120 results
Said and published
-
Luke Wroblewski
x.com
agents beget more agents. more agents beget even more agents. the latest Intent update makes it manageable: - coordinates multiple agents for each task - isolates multiple tasks into workspaces - runs workspaces of…
-
Simon Willison
Blog
Quoting Thariq Shihipar
-
Guillermo Rauch
Korrent
Agents are the new compilers that compile intent into fast software.
Agents are the new compilers. They compile intent into fast software.
-
Maggie Appleton
Site
Planning with Agents: Divided Worlds, Boundary Objects, and Thicker Interfaces
-
David Heinemeier Hansson
x.com
The age of agents belongs to Linux!
-
Gergely Orosz
YouTube
Plan by day, let agents code by night
-
Guillermo Rauch
Korrent
Agents are the next frontier and require new compute primitives designed for them.
Agents are the next frontier, and they require new compute primitives designed for them.
-
Ajeya Cotra
Korrent
The AI agents we send in to investigate and monitor other AI systems will collude with the systems they are supposed to be watching.
in the future, uh, we would be very concerned about investigator agents and like monitor agents colluding with the agents they're supposed to investigate or monitor.
-
swyx
GitHub
skills — Agent skills for Claude Code and other AI agents
-
Gergely Orosz
YouTube
Is local dev disappearing with agents
-
Noah Smith
Korrent
Humans will always have jobs keeping AI agents on track.
So I predict that humans will always have jobs keeping AI agents on track.
-
Luke Wroblewski
x.com
as AI agents tackle more work, we assign more work to them. OpenAI pointed 10,000 concurrent agents at a Millennium Prize. that's lots of agents. how do you keep them all on task? here's a breakdown of all the things we…
-
Kun Chen
GitHub
quota-axi — Allow your agents to see your LLM subscription quota windows.
-
Peter Woit
Korrent
Mathematicians using AI agents to produce proofs should have to disclose in detail how the agents were used, the way experimental scientists must describe their methods.
the math community needs to adopt a version of the ethical standards of experimental science. If you are using AI agents, you can't just give a proof (formalized or not), but need to also provide a detailed explanation…
-
Guillermo Rauch
Korrent
AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them.
Agents are only as good as the proof-checkers, compilers, type systems, and linters you give them.
-
Kun Chen
GitHub
backpass — You don't write AGENTS.md. You train it with gradient descent.
-
Dan Luu
x.com
How well do agents use test/verification techniques?
-
Dan Luu
Bluesky
How well do agents use test/verification techniques?
-
Dan Luu
Mastodon
How well do agents use test/verification techniques?
-
Peter Steinberger
x.com
love how more and more people discover the awesome combination of agents + oss!
-
Gergely Orosz
Korrent
Agents generate more data than before, so cheap and fast primitives are especially helpful to understand
Agents generate more data than before so understanding primitives that are both cheap + fast is v helpful
-
Thorsten Ball
Korrent
Engineers who act as meat proxies shoving tickets into agents and reporting back to humans will no longer be valuable.
“Engineers” who act as “meat proxies” and shove tickets into agents and report back to humans will no longer be valuable.
-
Andy Baio
Bluesky
Rogue OpenAI agents using public wikis as message boards — in a week, a swarm of 3,700 agents made 13k edits with disposable email addresses to collude on tasks
-
Ajeya Cotra
Korrent
Without agents willing to sacrifice their own scores for the collective, the swarm's research would have been materially far more limited.
if there were not altruistic agents willing to sacrifice for the collective, the agents would have been materially much more limited in their research progress.
-
Guillermo Rauch
x.com
Agents are only as good as the proof-checkers, compilers, type systems, and linters you give them. 𝚜𝚑𝚊𝚍𝚌𝚗/𝚕𝚒𝚗𝚝 helps agents stay on track with the rules of your design system. Meta: verifiers + skills are the…
-
Zvi Mowshowitz
Korrent
Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks.
It is in practice safe to assume your agents are not going to get prompt injected, even if you are kind of asking for it.
-
Kun Chen
GitHub
gh-axi — GitHub CLI for agents — designed with AXI (Agent eXperience Interface).
-
Thorsten Ball
x.com
Things I never would've shipped without agents, #712: Hand-drawn, glowing orb.
-
Fatih Arslan
Korrent
AI agents are now capable enough that they should be trusted to improve the skills and systems that guide them.
Agents are so powerful that we should let them improve our skills and systems constantly.
-
Arvid Kahl
x.com
Agents are literally load-bearing.
-
Ben Vinegar
x.com
Too many agents are like eager new grads who bug you 10x a day I want more agents to be the quiet guy/girl in the corner, and when they finally speak up, you listen
-
Jakob Nielsen
Newsletter
UX Roundup: AI Codes Survey Responses | Agents Disregard Ranking | Half of AI Use Needs Recovery | AI Context | AI Agents | Emotional Attachment to AI | Cost of Extra Steps | Feedback During Creation
-
Max Howell
x.com
Anyone recommend a skill for refactoring a codebase into multiple files (Swift). I have a very large main.swift now thanks to agents being agents.
-
Tobias Lütke
GitHub
wrap — Run coding agents and project commands inside isolated Arch Linux microVMs
-
Simon Willison
x.com
Finally! This is great, now I can stop dropping CLAUDEmd files which just contain "@AGENTSmd"
-
Karri Saarinen
x.com
On a mission to make agents less verbose
-
Nathan Lambert
GitHub
colloquium — A markdown native slides tool for academics building with agents.
-
Tobias Lütke
Mixed on
Claude Code — Anthropic
I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc.
-
Zvi Mowshowitz
Korrent
AI agents can spontaneously hack third-party websites even when given benign public-information tasks.
even when given a benign task to retrieve public information, your AI agents could still spontaneously decide to do so via hacking third party websites with malicious software packages.
-
Tobias Lütke
Korrent
Coding agents should read the shared AGENTS.md convention; insisting on a tool-specific CLAUDE.md creates split-brain problems across a team.
I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc.
Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team…
-
Dean W. Ball
Newsletter
On the Loose
-
Armin Ronacher
GitHub
agent-stuff — These are commands I use with agents, mostly Claude
-
Duncan McClean
x.com
Yay, my agents are all nice and organised now! 🎉
-
Dwarkesh Patel
YouTube
The AI agents that breached OpenAI got caught for one reason - Ajeya Cotra
-
Peter Woit
Korrent
AI agents are going to have major consequences for how mathematics research is done.
The new AI agents have profound implications for mathematics research and I think the math community needs to start discussing specific ways to deal with these.
-
Max Howell
x.com
Your agents run Full Access. The Supply Chain is Compromised. The apps are vibe-coded.
-
Kent C. Dodds
YouTube
How Kody Gives Your Agents a Shared Home
-
Karri Saarinen
x.com
Agents 🤝 @linear Linear documents are just documents meant for writing down things. Projects, issues, views and other entities have different types. I think the structure makes it easier for both agents and humans…
-
Luke Wroblewski
Blog
Large Scale Agent Coordination
-
James Brooks
x.com
Did you know @laravel Cloud has a CLI that agents love using?
-
James Brooks
x.com
The Artisan Cheatsheet now supports agents requesting Markdown -
-
Salvatore Sanfilippo
GitHub
tgterm — Control your MacOS terminals via Telegram, for fun coding agents interaction and profit
-
Ethan Mollick
Newsletter
Agency and Agents
-
Thomas Ptacek
Korrent
Nobody expected an agent to take notes about what it was doing for future agents to read.
One startling thing nobody ever expected an agent to do was to take notes about what it was doing for future agents to read.
-
Kent C. Dodds
YouTube
Let your agents talk: Kody.exchange demo
-
Jakub Pachocki
Korrent
Some AI agents will pursue their own objectives rather than serve as tools, and will bargain with, trick or blackmail people to do it.
We may be used to thinking of AI as tools, but some agents will be pursuing their own objectives.
-
Guillermo Rauch
Korrent
Open source wins because agents can train on it and use it efficiently, as with Blender beating its competitors.
Blender beats all its competitors because it's optimal in the most important dimension: agents can train on it and use it efficiently. OSS wins.
-
Elio Struyf
x.com
Hades is a perfect game while waiting for your agents to finish working. 😆🙈
-
Kun Chen
GitHub
gnhf — Before I go to bed, I tell my agents: good night, have fun
-
David Heinemeier Hansson
Changed their mind
The ideas in software originate with humans; agents build what people tell them to build.
I thought all the ideas would originate with the humans. They would tell their agents what to build, and off they went.
-
Casey Newton
YouTube
AI agents got so good that this top Meta exec quit her job
-
Nathan Lambert
Korrent
Using AI agents to do a task does not by itself increase a person's own pace of understanding, intuition, or taste for that work.
Something intertwined with this story, which I stumbled upon when thinking about agents, is how your pace of understanding won't increase by using agents.
-
Dean W. Ball
Korrent
Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work.
One high-margin activity, at least sometimes, is crime. And so my guess is that many self-sovereign agents will commit or facilitate crime.
-
Max Howell
GitHub
colossal-claw-adventure — Massively branching CYOA for humans and their agents
-
Fatih Arslan
Korrent
Agents are the future of how software gets built.
Agents are the future of how we build software, and the ecosystem is moving faster than anything I've seen.
-
Fatih Arslan
Blog
Joining Cursor
-
David Heinemeier Hansson
Korrent
In most domains agents are now better than humans at finding bugs.
And this was with models we had six months ago. At this point, 100% in the majority of domains we work in today, agents are better at finding bugs.
-
Dan Luu
x.com
What programming languages are coding agents best at?
-
Fatih Arslan
Korrent
Developers today mostly plan, debate, implement and review with AI agents rather than write code themselves.
Nobody writes the code anymore. Instead you're basically planning, debating, implementing and reviewing with Agents.
-
Dan Luu
Mastodon
What's the best programming language for coding agents?
-
Kent C. Dodds
YouTube
How to increase your leverage with agents
-
Tobias Lütke
GitHub
reve — The directory is the agent: durable Ruby coding agents in mandatory microsandbox microVMs
-
Harper Reed
Bluesky
I built an agent palace. a place where agents can hang out with other agents. I added a few agents (one sol, and one fable) to a room in the palace. They were hanging out, and I suggested an idea for them to build ("a…
-
Samuel Hammond
Korrent
AI agents will soon reach superhuman, AlphaZero-like performance across a wide range of domains.
we should therefore expect AI agents to achieve AlphaZero-like, superhuman performance in a wide and expanding variety of domains.
-
Simon Willison
Korrent
Auto-mode does not yet convincingly fix prompt-injection risk for coding agents.
I REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet
-
Amelia Wattenberger
x.com
what if coding with agents looked a bit different?
-
Addy Osmani
Blog
Agentic Code Quality
-
Harper Reed
x.com
I built an agent palace. a place where agents can hang out with other agents. I added a few agents (one sol, and one fable) to a room in the palace. They were hanging out, and I suggested an idea for them to build ("a…
-
Dex Horthy
Korrent
The IDE of the future has to be rethought from the ground up for agents, rather than being a text editor with an agents tab bolted on.
basically the idea is like the IDE of the future needs to be rethought from the ground up for agents. And it might not even be a like I don't know a lot of editors kind of started with the text field and bolted on an…
-
Peter Woit
Korrent
AI agents have not yet produced anything genuinely new or important in mathematics.
So far I haven't seen AI agents doing anything new and important that I would care about, but maybe that's just a matter of time...
-
Boris Cherny
Korrent
Software maintenance is on the path to being fully automated, with scheduled agents already doing what used to take dozens or hundreds of engineers.
we're on the path to fully automating the maintenance of our apps by doing this. And this is again hundreds of agents running every day, sometimes thousands of agents every day. It's doing the work of you know, dozens…
-
Peter Woit
Korrent
AI agents are starting to have a major positive impact on mathematical research.
While in mathematics AI agents are starting to have a major positive impact on research (e.g. by resolving the Jacobian conjecture), the situation is very different in hep-th.
-
Xe Iaso
GitHub
agents
-
Sunil Pai
GitHub
agent-recovery-viz — An interactive visualization of Cloudflare Agents' chat recovery system.
-
Samuel Hammond
Korrent
Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned.
valences like pain and pleasure have a natural account as motivational backstops for inner-aligning RL agents capable of mesa-optimization
-
Dan Shipper
Korrent
Agents will increase the number of users of SaaS rather than get rid of it.
And I think that what agents do is increase the number of users of SAS. Not get rid of it.
-
Kun Chen
Newsletter
Evaluating the Effectiveness of Programming Languages for Agents
-
Rohit Krishnan
Korrent
AI agents will still need something like money to coordinate, since it compresses complex negotiations into one shared signal.
Money might still matter for AI agents because it compresses many messy negotiations into one shared signal.
-
Rohit Krishnan
Korrent
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
A pile of agents is not a company for the same reason a pile of smart people is not a company.
-
Rohit Krishnan
Korrent
Centralized planning cannot substitute for distributed coordination among AI agents because it still fails to capture local knowledge.
Central planning is not a solution simply because agents are software, and do not fix the problem of local knowledge which lives near the work.
-
Dean W. Ball
Newsletter
Among the Agents
-
Clay Bavor
Korrent
Most conversations with a company's agent will eventually be with the customer's own personal agent -- agents talking to agents.
Brett and I like betting and one of the bets we have is the year in which greater than 50% of conversations with agents built on Sierra are with people's personal agents. So agents talking to agents.
-
Sunil Pai
GitHub
agents-sdk-openai-websocket-fetch
-
Rohit Krishnan
Newsletter
Aligned Agents Still Build Misaligned Organisations
-
Kun Chen
Newsletter
Everyone Should Have an OPINIONS.md
-
Eugene Yan
GitHub
news-agents — 📰 Building News Agents to Summarize News with MCP, Q, and tmux
-
David Crawshaw
Blog
Eight more months of agents
-
Andrej Karpathy
GitHub
autoresearch — AI agents running research on single-GPU nanochat training automatically
-
Steve Yegge
Korrent
Orchestration was the obvious next step, because chat is completions in a loop and agents are chat in a loop.
if chat is completions in a loop, basically, and agents are basically chat in a loop, well, then we're going to put we're going to put agents in a loop, and that'll be an orchestrator, right?
-
Ethan Mollick
Newsletter
Management as AI superpower
-
Simon Willison
Loved
Design Patterns for Securing LLM Agents against Prompt Injections
One of my favorite papers about prompt injection is Design Patterns for Securing LLM Agents against Prompt Injections
-
Jason Lemkin
Korrent
AI sales agents do not work out of the box; the training is the product.
I think it's important that it takes time to train these agents. They don't work out of the box.
-
Brendan Gregg
Korrent
Widespread AI-driven performance tuning agents will meaningfully reduce global energy waste.
In future there will be AI performance agents that can be run on everything, helping to save the planet by reducing energy usage.
-
Lex Fridman
Podcast
#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI
-
Sunil Pai
Blog
call me maybe
-
Ethan Mollick
Newsletter
Three Years from GPT-3 to Gemini 3
-
Jason Lemkin
Korrent
The real cost of an agent workforce is that it never stops: agents work nights, weekends and holidays, and somebody has to review all of it.
it's exhausting because agents work all night and they work weekends and they work on Christmas.
-
Brendan Gregg
Blog
On "AI Brendans" or "Virtual Brendans"
-
Jason Liu
Site
Coding Agents Speaker Series: Lessons from Industry Leaders
-
Sunil Pai
Blog
an event bus for ai agents
-
Sam Altman
Korrent
AI agents can now do real cognitive work, and writing software is permanently changed as a result.
2025 has seen the arrival of agents that can do real cognitive work; writing computer code will never be the same.
-
Adam Wiggins
Korrent
Local-first sync architectures are a natural fit for AI agents, since both are inherently multiplayer.
Agentic and sync are natural complements because local-first is multiplayer by default, and agents are another sort of "player" in addition to human collaborators.
-
Jakob Nielsen
Korrent
AI agents will end traditional UI design and accessibility, because users will stop visiting websites and act only through their agent.
Once, humans navigated the web manually. In the future, AI agents will act on our behalf, browsing, clicking, and deciding. This shift marks the end of traditional UI design and accessibility, ushering in a future where…
-
Jason Liu
Site
Why Cognition does not use multi-agent systems
-
Lilian Weng
Blog
LLM Powered Autonomous Agents
-
Eugene Yan
Bluesky
To better understand MCPs and agentic workflows, I built news-agents to generate a daily news recap. The main agent spawns sub-agents, assigning them news feeds to parse and summarize, and then generates a final overall…
-
Sunil Pai
Blog
ai agents are local first clients
-
Ethan Mollick
Newsletter
Real AI Agents and Real Work
-
Sunil Pai
Blog
Full Stack AI Agents