Summary of Judo Olympic Qualification Video

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

Let me try to grab the transcript directly with yt-dlp:

Written to ~/Downloads/boris-cherny-how-we-built-claude-code.md.

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.