User runs Codex on 15 years of X archive, producing a sentiment portrait of ~560K tweets
Yamapama · x · 2026-10-28
User Yamapama downloaded his X archive and let Codex analyze it, producing a sentiment report covering roughly 560K tweets from 2011-2026: 33.3% neutral, 23.2% joy, 18.3% humor, 11.8% anger, plus smaller shares of uncertain/calm/sadness/disgust, with per-year tone breakdowns peaking at 62,181 tweets in 2015. A fun, replicable example of using coding agents as personal data analysis tools.
Related event: Developer Feeds 15 Years of X Archive to Codex for Analysis(4 posts)→
More from coding & agent
- Enterprise workflow automation is still in its 'autocomplete era' — but not for long — saranormous · 2026-10-28
- Garry Tan shows his Capy AI software factory: 10-20 subagents running constantly, 19,101 contributions/year — garrytan · 2026-10-28
- Developers report Apple is automating App Review, with trusted accounts approved almost instantly — rudrank · 2026-10-28
- N-queens solved entirely in Python type annotations with ty, each solution a tuple — charliermarsh · 2026-10-28
- MCP gap: services can't push to agents, dev argues spec needs server-initiated events — braelyn_ai · 2026-10-28
- Swarms Cloud revamps Models page aggregating 2,000+ LLMs with pricing — KyeGomezB · 2026-10-28