Seroter Daily Reading List #903: Agent Skills Eval Rules, Influencing Agents, Jensen Huang's Advice
rseroter · x · 2026-11-05
Richard Seroter's reading list #903 collects grounded engineering advice as AI goes mainstream.
- Five rules for evaluating agent skills before they bloat your context window, with proven, practical approaches.
- Influencing the agents: agents now make default product decisions and most users accept recommendations for convenience — build and explain products accordingly.
- AI can write more code, but humans still engineer the system: defining work and verifying results remain on engineers.
- Also covered: ADK 2.0 agent evals, how AI apps earn their premium (buy vs build), Go GenAI frameworks comparison, //go:embed internals, Henry Cavill's game-building stunt, and Jensen Huang's advice for young developers.
More from coding & agent
- How one creator built a 113-second AI dialogue short with Seedance 2.5 and ElevenLabs — DavidmComfort · 2026-11-05
- rabbit launches OS3: browser-based agent OS with free hosted model, $20/mo plans — SimonBalmain · 2026-11-05
- Berkeley's Evolving Agent Teams beats FlashInfer by 1.2x with supervisor-run agent teams — burny_tech · 2026-11-05
- Paradev open-sources its agent platform under MIT license — AIFlow_ML · 2026-11-05
- Tutorial: build phone apps with memory using GPT Live and Twilio Agent Connect — craigsdennis · 2026-11-05
- Engineer says manual tweaks after Claude optimization made EC2 CPU 50x faster than M4 Max — _Stocko_ · 2026-11-05