# Trace: Summary of Judo Olympic Qualification Video Agent: pi | Model: Claude Opus 4.6 | Project: brightsavers --- ## User summarize https://www.youtube.com/watch?v=PQU9o_5rHC4 ## Assistant ## Assistant ## Assistant ## Assistant Let me try to grab the transcript directly with `yt-dlp`: ## User summarize https://www.youtube.com/watch?v=PQU9o_5rHC4 ## Assistant ## Assistant ## Assistant ## Summary: "Boris Cherny: How We Built Claude Code" (YC Light Cone Podcast) Boris Cherny, the creator/lead engineer of Claude Code, joins the Y Combinator Light Cone podcast to share the origin story, design philosophy, and future vision of Claude Code. --- ### Origin Story - Boris joined Anthropic's "Labs" team, which produced three products: Claude Code, MCP, and the Desktop app - **It started as an accident** — he built a simple terminal chat app just to learn the Anthropic API. Nobody asked him to build a CLI. - He gave it the **bash tool** (literally copied from the docs), asked it to read a file, then asked "what music am I listening to?" — it wrote AppleScript to query his Mac. That was his first "feel the AGI" moment: *"The model just wants to use tools. That's all it wants."* - **2 days after the prototype**, teammates were already using it to code. Internal adoption went vertical — Dario asked if engineers were being forced to use it. They weren't. ### Key Design Principles 1. **Build for the model 6 months from now, not today.** Early on, Claude Code couldn't really write code well. Boris wrote ~90% of his code by hand in Feb 2024. But they bet the model would get good at it — and it did. 2. **Latent demand is everything.** Every feature came from watching what users were *already trying to do*: - **CLAUDE.md** — users were already writing markdown instruction files for the model - **Plan mode** — users were already telling Claude "think about this but don't code yet." Boris built it in 30 minutes on a Sunday night, shipped Monday morning. *"All plan mode does is add one sentence to the prompt: 'please don't code.'"* 3. **The Bitter Lesson** — They have a framed copy of Rich Sutton's essay on the wall. Never bet against the model. Any "scaffolding" you build to improve performance 10-20% will be wiped out by the next model. So they constantly rewrite: *"There is no part of Claude Code that was around 6 months ago."* 4. **The terminal was an accident** — chosen because it was the cheapest UI to build. Boris expected it to last 3 months. He's been wrong — it's still the primary interface. ### How the Team Works - Boris considers himself an "average engineer" — uses VS Code, not Vim - He's been **100% Claude Code, no IDE** since Opus 4.5, landing ~20 PRs/day - His personal CLAUDE.md is just **2 lines**: (1) enable automerge on PRs, (2) post PRs to the team Slack channel. Everything else lives in the repo-level CLAUDE.md that the whole team maintains. - Advice on CLAUDE.md: **delete it and start fresh** if it gets bloated. Add back only what you need. With each model, you need less. ### Productivity Numbers - Anthropic team doubled in size, but **productivity per engineer grew 150%** since Claude Code launched (measured by PRs + cross-checked with commits) - Company-wide, 70-90% of code is written by Claude, many individuals at 100% - At Meta, Boris's previous job, a **2% productivity gain** took hundreds of people a year of work ### Sub-agents & Claude Teams - The **plugins feature** was entirely built by a swarm of agents over a weekend with minimal human intervention — one agent created an Asana board, spawned sub-agents that picked up tasks - Boris uses plan mode for ~80% of sessions, running multiple tabs in parallel - **Plan mode has a "limited lifespan"** — the model is learning to enter plan mode on its own, and soon may not need it at all (*"Maybe in a month"*) ### Co-work (Desktop App) - Again, latent demand: people were using Claude Code for non-coding tasks (monitoring tomato plants, recovering wedding photos, finance). Designers, data scientists, and the finance team were all jumping through hoops to use a terminal tool. - Co-work was built in **~10 days**, 100% written by Claude Code. It's just Claude Code in a GUI wrapper with a VM sandbox and extra guardrails for non-technical users. ### Advice for Founders 1. **Build for the model 6 months out** — otherwise you'll find PMF today and get leapfrogged tomorrow 2. **Follow latent demand** — make the thing people are already trying to do easier 3. **Never bet against the model** (The Bitter Lesson) 4. **Hire for beginner's mindset** — ask candidates "when were you wrong?" The best engineers can admit mistakes and think from first principles 5. **Expect code to be disposable** — shelf life is now ~2 months ### Bold Predictions - Coding will be **"generally solved for everyone"** soon - The title "software engineer" will evolve toward "builder" or "product manager" - Everyone will code — PMs, designers, finance people (already happening at Anthropic) - The scarier upper bound: ASL-4 (recursively self-improving models) and potential for catastrophic misuse, which Anthropic is actively working to prevent ## User output this as a .md file in ~/Downloads ## Assistant Written to `~/Downloads/boris-cherny-how-we-built-claude-code.md`. ## User summarize https://www.youtube.com/watch?v=nrmbTcdO0vk using gemini ## Assistant ## Assistant ## Summary: Olympic Qualification Finally! — The Shintaro Higashi Show Shintaro Higashi and co-host David Kim break down the newly released **USA Judo Olympic qualification criteria** for the **LA 2028 Olympics**. --- ### New Qualification Structure - **Direct Qualification:** Athletes can qualify by reaching the **top 17 in the IJF world rankings** - **Domestic Trials:** If no one in a weight class qualifies directly, USA Judo will hold an **8-person Olympic Trial** - **Full Team Opportunity:** Unlike previous cycles where the US only sent a handful of athletes, the current rules make it much more likely the US fills all **14 slots** (7 men, 7 women) ### Evaluation Criteria - Athletes will be selected for trials based on international performance + three key domestic tournaments: - **President's Cup** (typically November) - **Two upcoming National Championships** - The evaluation process is somewhat subjective ("squishy") — no strict point system for domestic trials yet ### The "Veteran" Factor - The easier path might entice older competitors to try for a spot (Shintaro half-jokingly considers a comeback) - They discuss **Tokuzo Takahashi**, a veteran who recently competed at the Tokyo Grand Slam, as someone still "in the mix" against younger athletes like Daniel Lyubomirisky ### Historical Context & "Gaming" the System - In the past (e.g., 2008), the US had more robust trials, but qualifying got harder as the IJF shifted to a points-heavy international circuit - Athletes used to farm points at "easier" continental opens (Oceania, Africa); now points are more proportional to tournament difficulty ### Bottom Line **2028 represents the best chance for US judokas to make an Olympic team since 2008.** The opening of 14 potential spots creates a high-stakes environment for both rising stars and seasoned veterans.