Announcing the @Paradigm Frontiers 2026 speakers! Some of my favorite people on Crypto x AI x Robotics x Devtools. @rauchg / Vercel @LegNeato / VectorWare @fat / Pierre Computer Company @sqs / Amp @SurajNair_1 / Physical Intelligence @0xKitsune / Tempo @danrobinson / Paradigm+Tempo Oct 12-14 - Fort Mason, San Francisco Apply by Aug 20th below.

Ever seen "ONLY SEND X TO THIS ADDRESS, ANYTHING ELSE WILL BE LOST" and sweated as you sent your transaction? Gone are these days, we built receive policies to solve this class of problems for every day users.

Frontiers by @Paradigm returns to San Francisco on October 12-14, 2026! Frontiers is our intense annual conference & hackathon for those beyond the edge. No booths, no sponsors, curated audience, stablecoins, ai, robotics, post-quantum cryptography and more. Apply below!

Plz take the extra effort to own your data and your infrastructure, assign 1 person on your team to set up Centaur over Claude Tag and let me know how it goes - docs in reply. Claude Tag is awesome, I've spent a few reps using it to understand where it does better than our OSS alternative (just memory right now which we'll have next week and have intentionally delayed because we didn't think it was worth it) but it's just hard to risk your entire company's brain atrophying if that were to be taken away from you. And soon we'll allow you to swap out frontier models for finetuned OSS ones on each channel (working on the eval rn) and then your cost is going to be in the low tens of thousands per year vs 10-100x that, plus you owning it all. That's the catch the forces above us don't want you to know.

Centaur is open source Claude Tag on steroids. Our most recent release unlocks adding Centaur to external channels, allowing untrusted input. This is a game changer, extending Centaur to a virtual coworker that you can add in any Slack Connect channel. Link below.

Any user reviews from Claude Tag from non anthropic employees? We've been building an open source competitor (Centaur) and looking to understand where it's strong and where it's weak UX wise. We have parity at allowing channel specific config, proxied secrets, workflows/crons etc, and are considering what's next. It also obviously works with any frontend (thx @vercel Chat SDK) and any sandbox backend (we provide a Kube one but trivial to add Modal, E2B or other). I've been pretty excited about a progressive replacement module where as more data in a channel gets collected you can replace a lab model with a finetuned OSS one that's cheaper (similar to the Thinky piece) but also weighing against other improvements. What do people think?

pretty incredible to see @patrickc casually mentioning to @sama the agentic infra we built in January for @tempo and @paradigm to transform how we work. we indeed use this to orchestrate pretty much anything at both companies. neither paradigm nor tempo can live without this now. it feels like the stone age without it. and because our organizations are so workflow heavy / data rich and we are <100 people, these are the perfect organizations to max deploy ai. it is natively multiplayer, harness agnostic, has secure secret management & firewalls, durable workflows, observable so it can self-improve/heal and most importantly - all self-hosted on bare metal & self-built, end to end. no third parties involved. we have two deploys, one for each company on different machines, but they both have a shared core codebase that's modular and extensible for each company's idiosyncracies. we're looking to do way more things with it. proactive agents remains an open problem for us. we hope to open source it very soon as i've mentioned a few times before. we're adding 1 special eng to that team, dm me + your proof of work if you're epic at infrastructure / security and love hacking things quickly.