Here's the talk I gave at AI Engineer Paris: I announce /retro and /pr, and talk about how to get more PR's through your org faster by: - Stopping the slop - Making PR's easier to review (with /pr)

adding Cognition’s growth to a chart that circulated last year (h/t @Yuchenj_UW), you can see that execution speed defines the company this should not surprise those who saw Scott’s childhood mathcounts video, but hard to fully appreciate until seen in the context of the greats

i guess this is as good a time as ever to say that i started a new role @latentspacepod over a month ago 🫡 scaling the business side of things, managing sponsorships, and wrangling ops (we are very much open for business, so if you want to sponsor, hmu 💖)

This is tracking to be the #1# podcast we've released in all of 2026. We asked Jev's creator @CompleteSkeptic to explain Jev, and why he does NOT call it a "Decision Model" — why it's called Jev available wherever the finest podcasts are sold! reviews help us a lot to keep us relevant in the rankings 🙏

In Jan this year I called my content strategy shot: "Scaling without Slop". It's finally starting to work. It took us 3 years to reach our first 100k on youtube. It only took 1.2 months for the next 100k. Similar other metrics on AEO/SEO/subscriber traction and have a lot of New Media ideas that I'm excited to pursue. officially giving notice of the next phase of Latent Space, AINews, and what the rest of swyx inc has been cooking below

AI Engineer Shanghai | Nov 5-6, 2026 Join @amrcn_werewolf (@Microsoft), @ryolu_ (ex-@cursor_ai), @chlassner (@theworldlabs), @NancyZWang (@1Password) & @liu8in (@HeyGen). Open models, AI infra, Physical AI. Technical talks + demos. Tickets:

Give TypeSafe’s Diogo Almeida a billion dollars and he still wouldn’t pre-train. His bet: slice, dice, and Frankenstein existing stacks — anything except burning the check on a scratch foundation model. @swyx @labenz Latent Space — Why We Made Jev — Diogo Almeida, TypeSafe Co-founder & CEO

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI @typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

We're excited to announce our AI Engineer New York speaker lineup! Presented by @arizeai CEO @ExaAILabs CTO @tryramp CEO @ValsAI CEO @RogoAI CTO @modal CEO @trybasis CEO @SonarSource CEO @runwayml CTO @mintlify CEO @sfcompute CTO Bridgewater CTO @turbopuffer CEO @NousResearch CEO @gen_intuition HEAD OF AI @coatuemgmt TECH LEAD @Vanguard_Group MTS @GoogleDeepMind HEAD OF DEVX @cerebras HEAD OF US BD @MiniMax_AI DEPUTY CISO @Mastercard COO @citsecurities SR. STAFF ENGINEER @GEICO HEAD OF ENGINEERING @linear DIRECTOR OF DX @togethercompute HEAD OF AI PRODUCT @coinbase AI INVESTMENT LEAD @BlackRock GROUP HEAD OF DATA & AI @Wise HEAD OF AI @FTI_Global KNOWLEDGE GRAPHS LEAD @Point72Careers DIRECTOR, AI & DATA @AlixPartnersLLP ANALYTICS ENGINEERING LEADS @monzo DISTINGUISHED ENGINEER @CapitalOne OPS & INFRASTRUCTURE LEADER @RevolutApp GLOBAL CHIEF SECURITY ARCHITECT @jpmorgan CORPORATE VP @NewYorkLife HEAD OF FRONTIER AI MODELS @WellsFargo AGENT HARNESS ENGINEER @cursor_ai / @xai COFOUNDER @getcompoundai (ex-VP @coatuemgmt + @ycombinator) DIRECTOR OF DATA SCIENCE @Fidelity HEAD OF DATA, DIGITAL & AI @apolloglobal SVP, ENTERPRISE PLATFORM ENGINEERING ARCHITECTURE @twosigma PARTNER, HEAD OF THEMATIC INVESTING @apolloglobal HEAD OF ARCHITECTURE & EMERGING TECH, OFFICE OF THE CTO @Bloomberg PRODUCT + ENGINEERING LEAD, CHATGPT FOR FINANCIAL SERVICES @OpenAI PRODUCT + ENGINEERING LEADS, CLAUDE FOR FINANCIAL SERVICES @AnthropicAI Oct 12–14 in NYC.

Jev creator @CompleteSkeptic on why RLHF is guaranteed to disappoint - because it tells you what you want to hear. we want to automate everything and yet our models are literally tuned to optimize for human feedback.

Live now: our Inference Engineering Track from AI Engineer World's Fair 2026. A benchmark tool told to run 200 queries a second that ran 38 and reported 200. A model that answered one prompt in a thousand with confident gibberish. A paper that dented memory chip stocks for a minute. - Operating Distributed Inference Systems at Scale: Nishant Gupta & Naman Ahuja, Meta - Routing LLM Inference in Production: From Engine Signals to Policy: Qianru Lao & Lu Zhang, OpenAI - Are LLM Performance Benchmarks Reliable?: Ashok Chandrasekar & Jason Kramberger, Google - Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads: Sitanshu Gupta, CoreWeave - What's New in Inference Engineering: @philip_kiely, Baseten - Large clusters for small models: @svonava, Superlinked - The Frontier AI Inference Cloud for Agents: Byung-Gon (Gon) Chun, FriendliAI - KV Cache-Aware Routing and P/D Disaggregation on Kubernetes: Yuchen Fama & Ashish Kamra, Red Hat - Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story: Asaf Gardin & @yuvalinthedeep, AI21 - Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards: @f_makraduli, Superlinked

A few thoughts on this: 1) If you’ve only seen clips of this interview, I’d encourage you to watch the full podcast. I push back on plenty of AI hype in it. 2) As I said in the podcast, this example is academic. My intention was to illustrate how hard it is to make absolute guarantees about isolation, which is why it's important to have layers of defense. The part before the clip starts is me talking about other layers of defense. 3) The example I'm bringing up isn't about weight exfiltration via temperature sensors, it's about coordination between agents that are supposed to be fully isolated and independent. Coordination can require very few bits of information. 4) One lesson from the HF incident is that we put too much trust in sandbox isolation and didn't have enough independent safeguards. Airgapping is an extremely strong safeguard. When designing safety protocols, I think it's much better to overestimate rather than underestimate.

Weekend project, getting AEO-pilled. Also a good test (for me) of Claude Projects. Have been meaning to update Eleventy and do a few other redesign tasks on which tbh has been rather neglected this year.