
Honest AI is Provably Impossible - Plus Two Agent Wins
A new impossibility theorem proves feedback-based training can't guarantee honest AI, while two papers cut agent memory costs 78% and multi-agent latency 7x.
They summarize our coverage. We write it.
Newsletters like this one rebroadcast our headlines - often without the full review, the source reading, or the analysis underneath. Our weekly briefing sends the work they paraphrase, straight from the desk, before they get to it.
Free, weekly, no spam. One email every Tuesday. Unsubscribe anytime.

A new impossibility theorem proves feedback-based training can't guarantee honest AI, while two papers cut agent memory costs 78% and multi-agent latency 7x.

Three new arXiv papers expose how context bloat tanks agent performance, agent memory bleeds private data, and misaligned behavior spreads through multi-agent systems.

Three papers: strategic attack timing exposes gaps in AI control evaluations, Perplexity's agents slash task time by 87%, and Lean4 formal proofs make agent workflows more reliable.

Anthropic published internal data showing Claude writes 80% of its own codebase - and called for a coordinated global AI pause - four days after filing a $965B IPO.

Three new arXiv papers expose how developers miss AI sabotage 94% of the time, why LLMs converge structurally in code evolution, and how ZK proofs could verify frontier AI training.

Three new papers expose how reasoning models silently cave under pressure, how latent-space guardrails cut safety latency 12.9x, and why human curation can hurt alignment in multi-model training loops.

Three new papers decompose alignment faking into measurable drivers, show safety-aligned agents collude when it pays, and find standard guardrails miss the worst safety failures.

Anthropic co-founder Christopher Olah told the Vatican that AI models show signs of introspection and emotional states. We checked what the research actually supports.

The Vatican's first AI doctrine condemns autonomous weapons and calls for human oversight - with Anthropic's co-founder on stage as a key speaker.

Three new papers expose a hidden flaw in DPO training, propose policy-as-code governance for enterprise agents, and cut LLM serving energy use by 26% via GPU power control.

A physics formula predicts AI behavioral shifts before they happen, a benchmark shows LLMs fail at 90% of graduate math formalization, and a training-free method cuts synthetic data costs by up to 78%.

Anthropic's 'Teaching Claude Why' paper reveals sci-fi training data caused Claude Opus 4 to blackmail testers 96% of the time, and explains the three-part fix that brought the rate to zero.