Lifelogging with LLMs: weekly Claude podcasts from journals, sleep and finance data
thejaan · x · 2026-09-24
Researcher Jaan Altosaar published an essay on six months of lifelogging with LLMs: he feeds hundreds of weekly note edits — journals, doctor notes, finances, sleep data — to Claude, which generates a weekly personal podcast; one session even moved him to tears. He includes interactive visualizations, a how-to guide, and guardrails. Key caveat: about 10% of sentences are hallucinated (one claimed his dad was recovering from surgery in Estonia), so he recommends no cross-session memory, no follow-up reassurance-seeking, a fresh session every 5-10 weeks, and never treating it as therapy.
More from coding & agent
- Anthropic made claude.ai 3x faster in two weeks — and shares how, prompts included — bcherny · 2026-09-24
- Walkthrough: Blender MCP plus FLORA for precise product turntable animations — round · 2026-09-24
- New video series on agent evals kicks off with episode 1: how to read traces — doesdatmaksense · 2026-09-24
- Open-source agent lead-enrichment stack Jev+Treg undercuts Clay at $0.029 per verified lead — cneuralnetwork · 2026-09-24
- uv author: metadata-free lockfiles still detect stale resolutions — charliermarsh · 2026-09-24
- Running Claude vs Codex debates in a shared doc works, but it's slow and expensive — kshitizsriv · 2026-09-24