Took @VictorTaelin’s awesome experiments around compressing GPT prompts and built CompressGPT. A one-line change in your @langchain code => 70% token usage deduction! musings.yasyf.com/compressgp…

Stepping outside my Stanford/Google/Waymo research bubble and sitting with real American companies made me realize why the bulk of the economy was not automatable by software or AI. We needed something new that is neither strictly code or AI, something that can flex but deliver reliable and affordable results to the biggest companies in the world. @tbpn @PoeticHQ

Introducing @PoeticHQ: a new AI system that executes complex multi-hour tasks with 99% accuracy and 10x fewer tokens than agents. We raised $50M at $500M from Kleiner Perkins, Founders Fund, First Harmonic, and Genius Ventures to build AI that does complex work inside Fortune 500 companies without hallucination. While code is too brittle, agents are too unpredictable. The work that runs the global economy - anti-money laundering, fraud investigations, underwriting - needs extreme accuracy. So we built a new kind of software that pairs the flexibility of AI with the predictability of code. When the world stays the same, Poetic runs fixed code: fast, cheap, identical every time. When the world changes, Poetic uses AI to regenerate its approach and find its way back to the objective. In one year, we went from zero to an eight-figure run rate as a team of four. Since then, we’ve scaled the team and executed the highest-stakes processes at AIG, SoFi, and Chime. At SoFi, a large US bank, Poetic reached 99% quality on fraud investigations in five weeks.

Sophons

I started talking to my co-founder like Claude

This is an insane paper and I love it arxiv.org/abs/2605.31514

.@superpower gives you a really cool “import from AI” onboarding experience… which does exactly nothing because the agent doesn’t have any tools to actually persist the data. smh another vacuous LLM product 😕

Today we're announcing our Series C funding: $355M at a $4.65B valuation, led by some great investors @generalcatalyst and @Redpoint. We've had insane growth in the last year, but we're still very early. So proud of the team and what we have built so far!

turbopuffer crossed $100M run-rate in March. 19mo after $1M. Profitable & <$1M raised. Cursor・Anthropic・Notion・Cognition・Harvey・Bridgewater・Ramp・Linear・Legora・Superhuman・Atlassian・Granola We’d be nowhere without them. We work like hell to exceed their expectations.

psa: your “unlimited minutes” cell plan is a lie & is actually capped at 44,640 minutes/month. wake up sheeple.

It’s 2018 and your coworker just sent you a 400 line pull request. You get a cup of coffee and sit down to review it. It’s beautiful. Elegant micro-refactors. Crispy method names. You catch a few things, but that’s ok. It’s part of the dance. They didn’t consider extensibility on part of their API. Here’s a comment buddy. They respond in an hour saying they think we should do one piece differently than your comment. Hey let’s jump into a room and figure it out. We can’t just agree to disagree, this code is too important. The PR merges and goes to prod. You feel a shared sense of ownership and accomplishment. That night you go to sleep and dream of that code. You can still see the shapes of it on the backs of your eyelids, your IDE syntax highlighting sparking neurons in your reptile brain. You go to work the next day ready to go. You understand the system. N is your foundation. Time to build n 1.

If your startup does not have a UUID microservice you’re ngmi

"AI code is crap." The shit your human engineers get up to:

-----BEGIN RSA PRIVATE KEY-----

it finally happened lol

we accidentally created a time capsule of the last era in which humans wrote code

glad I’m not the only one swearing at Claude at 2am…

I'm thrilled to announce @SycamoreLabs, the trusted agent OS for the enterprise. We raised a $65M seed led by @coatuemgmt and @lightspeedvp, with @AbstractVC, @DellTechCapital, @8vc, @Fellows_Fund, @e14fund, and an exceptional group of angel investors.

I'm excited to open source Chandra OCR 2! - 85.9% (sota) on olmocr bench - 90 language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts captions images and diagrams - Strong handwriting, math, form, table support

This is the era of the one-person marketing team. Launch dozens of high-performing landing pages from Claude and Clay. Using @tryflint’s MCP and API.

by far the coolest thing I’ve seen all month