Jérémy

GStack is an open-source toolkit built by YC President & CEO @garrytan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing. In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.

Today, we’re introducing Skills in @GoogleChrome, a new way to build one-click workflows for your most frequently used AI prompts — like asking for ingredient substitutions to make a recipe vegan, generating side-by-side shopping comparisons across multiple tabs, or scanning long docs to get the info you need quickly. When you write a prompt that you want to use again, you can save it as a Skill directly from your chat history. The next time you need it, select your saved Skill in Gemini in Chrome by typing forward slash ( / ) or clicking the plus sign ( + ) button, and your Skill will run on the page you’re viewing, along with any other tabs you select.

People of pi (x2)! Also updated my processes extension! pi add npm:@aliou/pi-processes Let your agent run processes in the bg, read logs + get alerted on errors! Works pretty well with TDD (if writing tests is still a thing that you do 💀)

"AI-First Is Not the Same as Using AI" Really cool article and nice discussions in the thread below!

Turns out we can get SOTA on agentic benchmarks with a simple test-time method! Excited to introduce LLM-as-a-Verifier. Test-time scaling is effective, but picking the "winner" among many candidates is the bottleneck. We introduce a way to extract a cleaner signal from the model: 1️⃣ Ask the LLM to rank results on a scale of 1-k 2️⃣ Use the log-probs of those rank tokens to calculate an expected score You can get a verification score in a single sampling pass per candidate pair. Blog: llm-as-a-verifier.notion.site Code: llm-as-a-verifier.github.io Led by @jackyk02 and in collaboration with a great team: @shululi256, @pranav_atreya, @liu_yuejiang, @drmapavone, @istoica05

Memory is not an optional plugin!

It was on a funniest feature I work on, congrats to the team! 🎉

“Some years you win, some years you build character” - Steve Jobs

"we hope to open-source future versions of the model" 👀

Please avoid to have issues/be down everyday first 😭

Using it with @marvinaziz for a few weeks now, it's pretty solid!

Been waiting for someone to crack memory for agents. This repo is 3 days old and already looks like the most promising attempt I've seen github.com/milla-jovovich…

Too many @GoogleChrome tabs open? Try vertical tabs, rolling out now. Just right-click any Chrome window and select “Show Tabs Vertically” to move your tabs to the side of the browser window, making it easier to read page titles and manage tab groups.

My roommate has been heads down on agentic workflows for 3 months and just put everything he learned into one article. I've been stealing ideas from him for weeks, now you can too 👀

100% agree!!

Friends in town. We did Alcatraz, Downtown Thursday, the Piers, a game at the Chase Center (Wemby you da best 😍), Muir Woods, Presidio hike and the bridge. Jesus Party Sunday at Dolores. Any recommendations for Monday before their flight? 👀

⚠️SFO Travelers: FAA just banned parallel landings Max arrivals reduce from 54 to 36/hour (30%) See the graph? Some flights at 9-11am, 3pm, and 8-9pm must be moved off-peak. Expect rescheduling, bigger aircraft, and norm of ~30 min delays. flighty.com/airports/san-f…

First day off for a while, Claude Code code leaked 🥲

Bought a tennis racket on Saturday. Came back Sunday and my roommate had already vibe coded a full mobile app to see all tennis courts in SF and reserve one in one click 😎

A very special guest on this episode of the Lightcone! @bcherny, the creator of Claude Code, sits down to share the incredible journey of developing one of the most transformative coding tools of the AI era. 00:00 Intro 01:45 The most surprising moment in the rise of Claude Code 02:38 How Boris came up with the idea for Claude Code 05:38 The elegant simplicity of terminals 07:09 The first use cases 09:00 What’s in Boris’ CLAUDE.md? 11:29 How do you decide the terminal’s verbosity? 15:44 Beginner’s mindset is key as the models improve 18:56 Hyper specialists vs hyper generalists 21:51 The vision for Claude teams 23:48 Subagents 25:12 A world without plan mode? 28:38 Tips for founders to build for the future 30:07 How much life does the terminal still have? 30:57 Advice for dev tool founders 32:11 Claude Code and TypeScript parallels 35:34 Designing for the terminal was hard 37:36 Other advice for builders 40:31 Productivity per engineer 41:36 Why Boris chose to join Anthropic 44:46 How coding will change 46:22 Outro