Things I Learned

[karpathy/autoresearch] is a concept/framework that allows one to leverage LLM to run an optimization loops based on a criteria. davebcn87/pi-autoresearch takes this further has built a generic optimization long run loop method on top of pi agent. gemini

Dynamic workflows in Claude Code. Claude dynamically writes orchestration scripts that spawn tens to hundreds of parallel subagents. It plans, decomposes into subtasks, fans out agents, and checks results before returning a coordinated answer. Adversarial agents try to refute findings, iterating until convergence. Enable via ultracode setting or ask Claude to “create a workflow”. Notable: Jarred Sumner used it to port Bun from Zig to Rust (~750K lines, 11 days). Available on Max, Team, Enterprise plans. Consumes significantly more tokens than typical sessions.

Use HTML instead of markdown to effectively plan and review. Claude Code: The Unreasonable Effectiveness of HTML" / X

colbymchenry/codegraph: Pre-indexed code knowledge graph for Claude Code — fewer tokens, fewer tool calls, 100% local

A good collection of practices on automated AI code reviews by Ankit Jain

• The Scalability Crisis: Manual post-PR review is no longer viable. AI agents have nearly doubled code output, causing human review time to spike by 91%, creating a bottleneck that traditional workflows cannot solve.
• The Upstream Pivot: Human value must shift from reviewing implementation to defining intent. Instead of checking syntax, humans spend their energy writing rigorous specs and acceptance criteria before the code is written, which the machine then uses to self-verify.
• The Swiss-Cheese Defense: Rather than one “perfect” human gate, the model uses a stack of imperfect automated layers. By layering signals like agent competition, deterministic guardrails, and adversarial “red-team” agents, the system catches errors where their individual failure modes don’t overlap.

codespelunker is a CLI code search tool that understands code structure and ranks results by relevance. No indexing required with CLI, TUI, MCP and HTTP support.

FluidVoice with paraquet v2 is soemthing i’ve been using now as my default speech-to-text on Mac, after evaluating WisperFlow, Handy and VoiceInk.

thaw a fork of Ice. I’m switching to it, as Ice seems to the inactive now.

mise let’s you manage dependencies at OS level and project level. Thinking to manage my dev machine. The hard part is documenting what I have installed.

Django Modern REST seems to be an emerging REST API library with focus on performance, scalability and pluggable serializers. Supporting msgpack, CBV and less of sync_to_async. Might evaluate it against the my current preferred django-ninja. gemini