The 2026 AI divide: digitized project context plus agentic tools like Claude Code
Afinetheorem · x · 2026-09-25
Afinetheorem argues the difference between people getting value from AI in 2026 comes down to two things: digitizing relevant project context, and using agentic tools like Claude Code and Codex — he keeps a spreadsheet of everything in his house and daily lab notes per project. In the quoted thread, another user describes running a full personal project system with ChatGPT Work by voice: Project Memory sheets and Status Brief docs in Drive, a central task list, the agent quizzing him on open items, searching his inbox and Slack, and even messaging teammates via Slack to fill gaps and update records.
More from coding & agent
- Stripe engineer answers 'what's it like at Stripe' with demos over memos culture — schwentker · 2026-09-25
- Perplexity's Fast Search costs $1 per 1,000 requests at 200 ms, 5x cheaper than standard search — AravSrinivas · 2026-09-25
- Wasmer runs a real PostgreSQL 18.4 server on iOS and in the browser via WebAssembly — jedisct1 · 2026-09-25
- Google Cloud details 4 patterns for real-time AI voice agents that see, talk, think and code — rseroter · 2026-09-25
- Opus 5.5 coded a polished 30-second hype video from one prompt in 3 hours of autonomous work — DaveRogenmoser · 2026-09-25
- NeurIPS Oral: IDS co-evolves code with formal proofs, hitting 3x Claude Code's success rate — adityagp · 2026-09-25