Learned memory put an older model at the top of a customer-service leaderboard without changing its weights. Amazon's Kiro now mines its own runs to propose prompt and tool fixes. Before paying for a model upgrade, builders should invest in loop design, memory and self-tuning harnesses.
From the Field Notes:
- Cheap, but unreliable. Smaller AI models are tempting for coding tasks because they cost less, and teams rarely choose a model on raw intelligence alone. (2026-10-22)
- ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model (2026-10-22)
- On Tuesday, Amazon unveiled Kiro-trace , an internal tracing system that improves Kiro, Amazon's AI coding agent, from its own runs. (2026-10-22)
- A Smarter Model Won’t Save Your Bad Harness (2026-10-22)
- Google launched agentic video understanding for Gemini Flash models, cutting long-form video costs up to 66%. (2026-10-22)