←
Sebastien Pahl2,098 posts
Sebastien Pahl avatar

Sebastien Pahl

@sebp

Senior Principal Systems Engineer @cloudflare ETI prev. @opstrace (co-founder/CEO, acq. by @gitlab), @redhat, @mesosphere, @cloudflare. @docker (co-founder)

◷ Joined December 2008▧ 108 Photos and videos
Sebastien Pahl avatar
Sebastien Pahl@sebp·Oct 23

Nice! And no Starlark in sight!

Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…

0:18
Simon Willison avatar
⟳ Sebastien Pahl retweeted
Simon Willison@simonw·Sep 28

I've published detailed notes and an annotated transcript to accompany the video of the keynote I gave at @WeAreDevs World Congress North America in San Jose on Friday - here's my rundown of everything that's happened with LLMs and agents in 2026 so far simonwillison.net/2026/Sep/2…

Dillon Mulroy avatar
⟳ Sebastien Pahl retweeted
Dillon Mulroy@dillon_mulroy·Aug 20

i’ve yet to see compelling evidence that not reading the code works. i’d be happy to be proven wrong.

DHH avatar
⟳ Sebastien Pahl retweeted
DHH@dhh·Aug 21

THE ANNOUNCEMENT: We’re going to make the prophecy of The Year of Linux on the Desktop come true. All the pieces are now in place. Time to go all in! omarchy.org/news/2026/08/oma…

kate avatar
⟳ Sebastien Pahl retweeted
kate@whoiskatrin·Jun 1

spent the evening building a cardputer client for codex can send tasks, watch edits come in, approve changes cardputer → cloudflare sandbox → codex kinda ridiculous, I know

Post attachmentPost attachmentPost attachmentPost attachment
OpenAI avatar
⟳ Sebastien Pahl retweeted
OpenAI@OpenAI·May 20

Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in 1946. For nearly 80 years, mathematicians believed the best possible solutions looked roughly like square grids. An OpenAI model has now disproved that belief, discovering an entirely new family of constructions that performs better. This marks the first time AI has autonomously solved a prominent open problem central to a field of mathematics.

2:38
Mike Nomitch avatar
⟳ Sebastien Pahl retweeted
Mike Nomitch@MikeNomitch·May 19

Excited to launch Claude Managed Agents on Cloudflare today! - Run sandboxes as microVMs or even lighter-weight isolates on CF - Zero-trust creds injection, custom egress proxies, better observability, private services via VPC - Agent Email + Browser Run + easy custom tool calls

Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your security controls applied by default.

0:15
kate avatar
⟳ Sebastien Pahl retweeted
kate@whoiskatrin·Apr 15

you can build a Python agent that accepts a coding task, executes it inside a Cloudflare Sandbox, and copies the output files to your local machine @OpenAIDevs x @CloudflareDev Check out our guide here: developers.cloudflare.com/sa…

Build long-running agents with more control over agent execution. New capabilities in the Agents SDK: • Run agents in controlled sandboxes • Inspect and customize the open-source harness • Control when memories are created and where they’re stored

Post attachment
Kenton Varda avatar
⟳ Sebastien Pahl retweeted
Kenton Varda@KentonVarda·Mar 25

One point of confusion I'm seeing: Lots of people assume you're supposed to run the AI agent harness itself inside a sandbox, and wonder how to do that with Dynamic Workers. The harness does *not* need to be in the sandbox. It can be a regular old Worker (probably a Durable Object, probably using Cloudflare Agents SDK[0]). Remember that an LLM can't manipulate the world at all unless you give it tools. So if you are careful about what tools you give it, it is inherently sandboxed. What we are proposing here is that you basically give the agent two tools: One to explore the APIs it has available to it (returning TypeScript type definitions), and one to execute code against those APIs (input is JavaScript). The latter tool runs the code in a Dynamic Isolate. You can't quite just run Claude Code or Codex in there, since they aren't designed to run in Workers, at least today. But @southpolesteve managed to get OpenCode (a similar harness) running 100% in Workers[1]. It's also not as hard as you might think to write your own harness -- I've done it. That said, if your agent's task specifically involves using a bunch of Linux programs, it may still be best to use containers for that. For instance, if your agent is doing software engineering -- checking out a git repo, running a compiler, etc. -- it may be impractical to make that all work in Workers. Try our Sandbox SDK[2] for that. But if your agent is planning a family vacation, it probably doesn't need to run rustc. It probably just needs to interact with a bunch of APIs. And that's where Dynamic Workers shine. blog.cloudflare.com/dynamic-… [0] developers.cloudflare.com/ag… [1] x.com/southpolesteve/status/… [2] developers.cloudflare.com/sa…

To show this off I slopforked the @opencode server so it runs entirely inside a @CloudflareDev Durable Object. No servers. No containers. Hibernates when idle. Try it: opencode attach opencode-do.southpolesteve.w… Code: github.com/southpolesteve/op…

Cloudflare avatar
⟳ Sebastien Pahl retweeted
Cloudflare@Cloudflare·Mar 24

We’re introducing Dynamic Workers, which allow you to execute AI-generated code in secure, lightweight isolates. This approach is 100 times faster than traditional containers. cfl.re/4c2NvPl

Steve Faulkner avatar
⟳ Sebastien Pahl retweeted
Steve Faulkner@southpolesteve·Mar 13

To show this off I slopforked the @opencode server so it runs entirely inside a @CloudflareDev Durable Object. No servers. No containers. Hibernates when idle. Try it: opencode attach opencode-do.southpolesteve.w… Code: github.com/southpolesteve/op…

OpenCode hasn't hyped it up but remote server support is really good. You can see where this is going. Excited to see the end state of what they build.

Darren Shepherd avatar
⟳ Sebastien Pahl retweeted
Darren Shepherd@ibuildthecloud·Feb 16

People stop asking this question. The answer is yes, it will always be yes. C is absolutely essential to understanding computers.

Do you think learning C programming is worth it in the era of artificial intelligence?

Pierre Beyssac 🏴‍☠️🇫🇷🇪🇺🇺🇦 avatar
⟳ Sebastien Pahl retweeted
Pierre Beyssac 🏴‍☠️🇫🇷🇪🇺🇺🇦@pbeyssac·Jan 28

Soudain je me souviens du traitement en France de la #copyrightdirective en 2019. Idem : la presse était pour, par intérêt direct parce que les ayants-droit lui avaient donné un bout de lard. Résultat, 100 % de la couverture en faveur. 1/2

Résumé de 100 % de la couverture média généralistes de la loi sur l'interdiction des réseaux sociaux aux moins de 15 ans : "super". Unanimité totale, y compris dans les émissions de débats, 0 recul, 0 contradiction. Les seules critiques regrettent que ça n'aille pas assez loin.