Full video of Anthropic’s Claude Code lead on model choice and token cost
rohanpaul_ai · x · 2026-07-27
This reply points to the full video of Anthropic’s Claude Code lead Boris Cherny talking about model usage and token cost.
- His core claim is that there may be limited room to optimize spend, but much larger upside in improving model returns.
- The practical advice is to stop over-focusing on token cutting and instead use the strongest model when it matters.
- The post links the full Scale video.
Related event: Anthropic Lead Urges Optimizing LLM Returns Over Token Costs(2 posts)→
More from coding & agent
- Opus may cost more than Fable on hard debugging when retries pile up — doodlestein · 2026-07-27
- Buzz agent team goes live with an 11-agent orchestration roster — builditwithjoe · 2026-07-27
- Swarms adds Frenzy Hub, redesigns Marketplace, and ships Gemini 3.6 Flash — KyeGomezB · 2026-07-27
- AI-Trader adds an MCP server so LLMs can run trading backtests — tom_doerr · 2026-07-27
- Anthropic’s Claude Code lead says token spend can be cut 50%, but returns may be 1,000x higher — rohanpaul_ai · 2026-07-27
- Sentient OS brings proactive computer-use agents to the Mac with an on-device LLM — TechExpert2910 · 2026-07-27