Using reservoir computers for real-time Bluesky "mass surveillance"
cephaloform · x · 2026-08-19
The author shares an experiment using reservoir computing to maintain a real-time 64k-dimensional state vector of the entire Bluesky platform. The system is simple enough to run on a Raspberry Pi. By training a readout layer to predict event classes based on states retro-labeled with news article timestamps, it demonstrates a basic form of "mass surveillance." The author wonders what a natural language autoencoder running on this state might say.
More from Research
- Stanford Team Wins Databricks Grounded Reasoning Cup With 63.3% Accuracy Via End-to-End Agent Optimization — jefrankle · 2026-08-19
- Study finds AI watermarking damages quality, especially at long context — mimi10v3 · 2026-08-19
- Grok 4.6 lands #2 on new DiligenceBench, statistically tied with Claude Opus 5 — karinanguyen · 2026-08-19
- GPT Doubles Formalized Erdős Solutions Over a Weekend, Proving Autoformalization Works — AlexKontorovich · 2026-08-19
- Building a Benchmark for Decomposition Attacks for Agents at AI Safety Night — chhaviyadav_ · 2026-08-19
- Researchers found 3 confirmed CVEs in Chromium, VirtualBox, QEMU for $609 — thedealdirector · 2026-08-19