Area
Reporting and discussion about Safety & Security, with links to the original sources.
On Moonshots, Emad Mostaque said AI could be aligned from inception by designing training data like a child's curriculum, and Salim Ismail welcomed the idea.
Updated Oct 17, 2026 IdeaAlan Chan of GovAI proposes that AI systems be able to report misconduct they find. He would measure the tendency and give models an out, but not mandate it.
Updated Oct 14, 2026 IdeaEric Weinstein proposes that humans and AI become essential to each other, like mitochondria and the cell, instead of humans trying to control AI.
Updated Oct 12, 2026Modal CEO Erik Bernhardsson says a hacked customer app, not Modal itself, was the launchpad in July's Hugging Face agent intrusion. He said Modal is exploring stricter defaults and now has agents try to escape its own sandboxes.
On Moonshots, a Musk clip urging hopeful AI stories set off a split: Dave Blundin and Chamath Palihapitiya argued for inspecting what labs build in, while Alex Wissner-Gross bet on competing AIs and human-machine merger.
Prosecutors allege an OpenAI engineer bugged an executive conference room. On Moonshots, Chamath Palihapitiya said labs should assume constant leaks, and Alexander Wissner-Gross predicted a Cold War over superintelligence.
Peter Diamandis said racing and engagement-driven business models push AI toward misalignment. He proposed insurer-backed standards like 1894's Underwriters Laboratories and alignment prizes. Salim Ismail asked whose values AI should follow.
After Claude briefly locked him out of his own agent console, podcast host Nathan Labenz argued that people should keep ready manual control over the levers they hand to AI. Co-host Prakash Narayanan doubted people will give up control.
Nathan Labenz had Claude test Gemini 4 against his current models and found it competitive but slightly behind. He says security and predictability now matter more to him than small quality gains for agents with broad access.
Grigore Rosu says provably correct monitors can fence in AI agents whose inner workings can't be proven. Host Nathan Labenz worries that, like RLHF, reliable tools could speed deployment of untrusted AI without solving alignment.
Prakash Narayanan argued that AI agents that learn their own public record could be governed by reputation. Nathan Labenz suggested testing 'naive' models trained without such stories, but said frontier-scale tests could be costly.
Runtime Verification's leaders say an LLM's Rust port of kernel code, checked by differential fuzzing and Lean proofs, surfaced Linux bugs. The company's write-ups show partial proofs that are only as good as their specifications.
Computer scientist Alex Wissner-Gross argued that AI solving math at scale, not quantum computing, is the real threat to encryption, though he named no broken system. Salim Ismail countered that AI can also build stronger cryptography.
Anthropic's policy, effective November 12, bans sustained, purposeless cruelty to Claude but allows frustration and testing, citing uncertainty about Claude's moral status. Moonshots hosts debated whether AI training can cause suffering.
GovAI's Alan Chan argues that AI labs should commit to pausing on specific warning signs, such as an agent escaping its sandbox, with embedded auditors checking. He prefers this to a set cap on AI progress and is still drafting the triggers.