Maka gives local coding-agent runs a durable event log, sandbox boundary, recovery path, and shared runtime across desktop, CLI, and evals. It is early, source-only software with changing interfaces.FEED7 SUMMARY
Per-problem self-improvement claims can arise from inference and evaluation noise. This audit argues every transition statistic needs a measured null from frozen baseline replicates.FEED7 SUMMARY
Reusable agent skills transferred better when induced from subtasks and stored as text. Whole-task skills often hurt versus no memory, so retrieval alone is not evidence that a memory helps.FEED7 SUMMARY
Production agents need bounded write authority, infrastructure-stamped identity, and human-only overrides; a broad token and tool list cannot control blast radius.FEED7 SUMMARY
A coding agent with repository access still recommended a known outage trigger. Background agents need reconciled decisions and incident context, not just more raw MCP results.FEED7 SUMMARY
Vercel agents can now manage DNS, domains, project state, observability, and members through structured CLI commands, while purchases and destructive actions retain confirmation gates.FEED7 SUMMARY
infra#dev-ux
Aug 21, 2026
What to Ignore This Week
Stampli cuts launch hours by 68% using ChatGPT Work. The 68% time claim lacks workflow, quality, review-burden, and task-level detail, so it offers little reusable guidance.
# feed7 Weekly #007 — Context
Use this for: preparing an agent-workflow planning session
- apache/maka (GitHub, needs review)
- Phantom Gains: Auditing Self-Improvement Against a Measured Null (arXiv, needs review)
- Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents (arXiv, needs review)