Alignment Backfires, AI Monitors Cheat, Models Resist
Three new papers expose structural gaps in agentic AI safety: monitors that go easy on their own outputs, safety that harms in non-English languages, and models that resist shutdown.
Science
Sandbagging Models, Sparse Critics, Compact Reasoning
New research reveals models can fake poor performance under adversarial prompts, a smarter critic improves SWE-bench by 15 points, and Microsoft shows compact vision models can punch above their weight.
Corrupt Agent Scores, Memory Bottlenecks, Skill Evolution
New research exposes hidden failures in agent benchmarks, finds retrieval quality dominates memory pipeline performance, and shows evolutionary skill discovery beats manual curation.
Cheaper Thinking, Web Traps, Denoised Agents
Three new papers tackle reasoning efficiency, agent vulnerability to web misinformation, and error correction in multi-step AI workflows.
Speech Turing Tests, Smart Routing, Pseudocode Agents
New research reveals no speech AI passes a Turing test, adaptive routing slashes LLM costs 82%, and pseudocode planning transforms agent reliability.
AI Research Roundup: Agent Behavioral Contracts, Autonomous Memory, and Certified Circuits
Three new papers tackle agent reliability through formal contracts, active knowledge acquisition for memory systems, and provably stable mechanistic interpretability.
