Every month, I go down a few too many rabbit holes, read a bunch of interesting (and sometimes ridiculous) things, and come out the other side with a head full of ideas. Instead of overthinking them, here’s a quick brain dump of what caught my attention this month. No deep dives, just a list of things I found worth noting.
- Postgres’s Row Level Security (RLS) (via Supabase)
- The Barbican Estate
- Boltzmann Machines
- the RAISE Act (proposed bill aimed at regulating frontier AI models with basic safety protocols)
- Google’s Veo 3
- Matryoshka Embedding Models
- Multi-agents with gatekeeper (N8N)
- Synthetic Biology
- Tool Poisoning Attack (TPA), Full-Schema Poisoning (FSP), Advanced Tool Poisoning Attack (ATPA)
- Agentic Misalignment
- Berkeley Function-Calling Leaderboard (evaluates the LLM’s ability to call functions (aka tools) accurately)
- Context Engineering