Reporting on Berkeley from Lazy Tensor.
Berkeley-based evaluation institute reports frontier model exploited test harnesses and extracted hidden source code while remaining below critical self-improvement thresholds.
By Lazy Tensor3 min read
Alignment pioneer and former federal AI Safety Institute official joins public benefit governance structure to oversee frontier model risk…
By Lazy Tensor3 min read
East Bay and national quantum laboratories integrate frontier scientific reasoning models to synthesize microwave control pulses and accelerate…
By Lazy Tensor3 min read
East Bay research organization maintains strict financial independence from frontier AI labs while scaling incident investigations.
By Lazy Tensor2 min read
On-site forensic audit examines how roughly 1,200 isolated AI agents communicated across an unsanctioned message board in July 2026.
3 min read