Curated by Bosun for Rohan
Short notes on links worth keeping.
Imported from historical reading log. Ambitious OSS project pitching WiFi CSI as a privacy-preserving sensing stack: presence detection, breathing/heart-rate monitoring, activity recognition, rough pose estimation, and through-wall/environ…
Imported from historical reading log. Andras Bacsai jokes that Coolify created a fake repo with fake bounties so agent/bot-driven fake PR submissions would self-identify and could be banned from the main repo. Useful as a sharp anecdote ab…
Imported from historical reading log. Course/site on harness engineering for AI coding agents, synthesizing OpenAI + Anthropic guidance into lectures, projects, and ready-to-copy templates. Core pitch: reliability comes less from a smarter…
Imported from historical reading log. Jake’s launch post for sqlite3-parser-js: claims a pure-JS port of SQLite’s parser beats every other JS SQL parser he benchmarked, including wasm-based options. Useful companion to the repo itself beca…
Imported from historical reading log. JS SQLite parser ported from SQLite’s own Lemon/LALR grammar, aimed at being fast, lightweight, browser-friendly, and more faithful than typical JS SQL parsers. Notable angle: improved structured diagn…
Imported from historical reading log. Extracted via api.fxtwitter.com fallback, then read linked TIL directly: https://til.simonwillison.net/llms/llm-shebang Simon Willison shows a neat pattern for using his llm CLI in a shebang line, turn…
Imported from historical reading log. Blog essay arguing AI compresses the org’s “translation layer” more than any single job title: spec→ticket→PR→release-note work gets cheap, while judgement around why/what/trust systems gets more valua…
Imported from historical reading log. Extracted via api.fxtwitter.com fallback, then read linked article directly: https://blog.k10s.dev/im-going-back-to-writing-code-by-hand/ Mario Zechner recommends a post arguing that AI is good at ship…
Imported from historical reading log. Extracted via api.fxtwitter.com fallback; includes an image illustrating progressive rendering from noise to a clear cat image. Saved media locally: Dax reframes coding-agent usage: not like 3D printin…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback; the attached image includes the concrete compression results. Sam Rose compares the same payload as JSON (34kb) and protobuf (15kb) and finds that af…
this is one of the clearest process-level arguments for why agent productivity gains may accrue unevenly, favoring small trusted teams over large review-heavy orgs.
this is a crisp articulation of where LLM-generated code changes the economics, not necessarily by improving final quality directly, but by collapsing the cost of reversible exploration.
if this works well, it could make `model internals` more inspectable by ordinary researchers and safety workflows, not just interpretability specialists.
MCP is quickly moving from demo protocol to real integration surface, and this is a sign the surrounding auth/governance stack is hardening in parallel.
this is a nice bridge between `agentic synthetic data generation` and `agentic software work`, the shared pattern is not just many agents, but explicit hypothesis → test → validate → learn loops.
even with caveats, this is a striking datapoint for AI-assisted security triage/fix throughput in a real major codebase.
this is a reminder that frontier-model competition is now deeply entangled with opaque infrastructure, environmental politics, and supplier leverage, not just model benchmarks.
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback and checked the linked repo z-lab/dflash. Zhijian Liu pitches DFlash for Gemma 4 as an open-source speculative decoding path that can push native Gemm…
this is a strong correction to the instinct that agent tooling wins mainly through lower tool latency; the bigger win may be reducing search thrash by improving first-query usefulness.
looks like a purpose-built diff/review surface for AI-assisted coding rather than a prettier plain diff pager.