Michele Catasta on X: "Continual Learning for Agents" / X
x.com · 2,350 words · saved by 1 readers
https://t.co/3BAeQ795hm
Everyone talks about Continual Learning as if it means one thing only: updating model weights. But there's an inconvenient truth about the agent ecosystem — the vast majority of agents in production today leverage closed frontier models. When you don't own the weights, you certainly can't fine-tune them. For most agent builders, weight-level continual learning is off the table, especially when working at the very frontier of capabilities (think Fable 5 or GPT 5.6). That doesn't mean agents can't learn. Agentic systems can improve at three layers — model, harness, and context [0] — and the…
saved by
related reading
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Harness Engineering for Self-Improvement | Lil'Loglilianweng.github.io
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Composer2.pdfcursor.com
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Building Effective AI Agents \ Anthropicanthropic.com
- AI agent evaluation frameworks for production - Vercelvercel.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Continually improving our agent harness · Cursorcursor.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Notes on the Software Factorybenedict.dev