Reading papers by walking: agents run experiments while you ask questions
yaroslavvb · x · 2026-09-11
yaroslavvb shares a mobile paper-reading workflow: listen to a 10-minute summary, hand agents GPUs, ask clarifying questions while walking, and review phone-readable experimental artifacts on the go. He open-sourced 'gradient dissent,' a critical review of the Don't Drop Dropout paper (arXiv:2609.05275) with exact counterexamples, locally executed toy experiments, interactive slides covering the method's four knobs, and connections to Sutro's energy-efficient learning agenda.
Related event: Engineer shares mobile paper-reading workflow and layer dropout findings(2 posts)→
More from coding & agent
- Tencent open-sources WeKnora, a RAG knowledge platform with 22k GitHub stars — abhishek__AI · 2026-09-11
- Tencent open-sources WeKnora, a RAG platform turning scattered docs into reasoning knowledge bases — abhishek__AI · 2026-09-11
- One Pokédex, four model setups: hands-on comparison of GPT-6 Astra and DeepSeek V4.1 Flash — kevinkern · 2026-09-11
- Agent Arena launches leaderboard grading models on millions of real agentic tasks — arena · 2026-09-11
- mcp-ecc: Open-Source MCP Server Unifying Email, Calendars and Contacts Across Providers — karljsamuel · 2026-09-11
- Codex Token usage surges post GPT-6 Astra; dev ships three Obsidian AI plugins — vista8 · 2026-09-11