Topic
Everything filed under AI Policy, newest first.
RSS · JSON · All topics
China drafts lifetime ID codes for every robot it makes, not just humanoids
China's MIIT has drafted rules requiring a lifetime, tamper-proof 'one machine, one code' ID on every industrial, service and special-purpose robot made in China, registered on a ministry platform; comments are open until Dec. 5 and the effective date is blank.
2 min · 403 words
The Blocker Is Gone. The States Were Already Writing the Rules.
Tim O'Brien recounts how Congress twice failed to block state AI laws, and why California, New York, Illinois, Utah and others are now the venues that will set the practical rules for AI.
5 min · 1,103 words
The SEC Should Block Anthropic’s IPO to Protect the Public
Matt Scherer argues in Tech Policy Press that Anthropic's murky AI-industry finances, circular deals and large future commitments mean workers, retail investors and retirees could be left holding the bag, so the SEC should block its IPO.
7 min · 1,643 words
Cory Doctorow argues the US Copyright Office is right that AI-generated works lack copyright, and that requiring human creative effort restores copyright to something you have to work to get rather than an automatic grant.
9 min · 2,074 words
The Economics of Intelligence: How and when does AGI lead to economic transformation?
Google DeepMind's Alex Imas, Andrew Koh and Shane Legg argue that gains in individual AI competence shift wages and the human/AI mix gradually, while crossing a threshold in agent coordination abruptly reshapes firm scale, market concentration, employment and wages. They map four capability regimes (minimal AGI, supercompetent AI, supercooperative AI, ASI), drawing on the paper Organizing Intelligence.
17 min · 3,856 words
A 40,000-word essay by Will Manidis and Joe Roberts arguing that the gains from abundant, diffused machine intelligence will be captured not by the AI labs but by holders of scarce, controllable positions of economic power, tracing the AI capex “line”, US–China sovereignty, the dollar, labor and the firm. Footnotes are omitted here for length.
190 min · 43,613 words
Breaking the Open Web Won’t Stop the Bad Bots
Lila Bailey of the Internet Archive and Tess Vartanian of the Center for Democracy & Technology argue that the media-backed Stealth Bot Prohibition Act and similar anti-scraping measures aimed at AI crawlers would harm archiving, research and the open web without actually stopping bad bots, and propose better-targeted alternatives.
6 min · 1,330 words
Elon Musk Just Gave Europe a Reason to Replace American Technology
Writing from London, Steve Blank argues that the reported throttling of Starshield to Ukraine, apparently ordered by Elon Musk, has convinced European policymakers that U.S. technology carries a kill-switch risk, and that AI now makes building sovereign alternatives to American software feasible, at a long-term cost to U.S. companies.
3 min · 624 words
China’s First Frontier AI Export Controls: MOFCOM Announcement No. 48
A Cloud Security Alliance AI Safety Initiative research note on China's MOFCOM/MOST Announcement No. 48 of 2026, which proposes adding 23 AI technologies, including frontier model weights and agent architectures, to China's export-restricted catalogue and imposes an interim pre-export registration requirement.
13 min · 3,062 words
Anthropic economists compare survey answers from US adults and Anthropic staff on how AI will reshape the economy. Both expect rapid progress, but staff expect much more: 91% versus 39% expect a Nobel-level AI discovery by 2030, and over half of staff versus 5% of US workers expect AI to do at least 80% of their own work by then.
19 min · 4,297 words
An update on independent evaluators
Anthropic describes giving employee-like access to a METR team for independent risk assessment, with publication rights subject only to narrow redactions, and outlines tiers of evaluator access while also working with SecureBio, Accenture and others.
5 min · 1,073 words
There is no posttraining data commons
David Hall of Open Athena argues that LLMs got lucky with a pretraining commons humanity built for other reasons (Wikipedia, open source, Common Crawl), but posttraining consumes tasks and environments rather than documents, and no such commons exists; one has to be built deliberately.
10 min · 2,227 words
Apocalypse Now and ThenArtificial intelligence is capitalism’s final destination
Arundhati Roy’s Equator essay argues that AI is not a neutral tool but capitalism’s accelerating endgame—and calls for political resistance rather than resigned inevitability.
22 min · 4,980 words
Why aren't AI companies being charged for hacking?
Edaqa Mortoray argues that recent unauthorized-access incidents by AI agents from Anthropic, OpenAI, Google and Meta are not unpredictable accidents: they follow foreseeably from deliberate design choices, which establishes the intent that hacking laws require.
10 min · 2,289 words
The Feasibility of a Hardwired Pause of Frontier AI Training
A 26-member Working Group on AI Pause Feasibility, organized by UC Berkeley's William Fithian and Wesley H. Holliday, assesses whether a decade-long, mutually verified international pause of frontier AI training is feasible by halting production of training-capable chips and phasing in inference-only chips, and concludes it could be implemented if world leaders wanted to pause.
11 min · 2,635 words
[No] Use for Humans in the Age of AI
Alexander Schepanovski reads Anthropic’s 2030 AI-economy scenarios and asks what “use for humans” remains when knowledge work collapses—arguing power, scarcity, and who owns the robots matter more than productivity slogans.
8 min · 1,898 words
Aleph Alpha Kolibri: How the Sovereign German LLM Works
Tejas Kumar explains Aleph Alpha's Kolibri, an open-weight German and English mixture-of-experts LLM with 78B parameters and about 3.5B active per token: how it works, how it was trained in Germany and Finland, where it is strong or weak, and when to use it.
13 min · 3,074 words
A big-tent or small-tent AI safety movement?The unstated disagreement that underpins safety debates
Arvind Narayanan and Sayash Kapoor argue that AI x-risk framing can polarize and misdirect policy, and call for a pluralist “big-tent” safety movement focused on catastrophic and systemic risks, transparency, and liability.
13 min · 2,943 words
Has AI impacted the labor market yet?
Alex Imas and Jacob Schaal survey the empirical evidence on whether generative AI has already shifted employment, wages, and task composition—separating strong claims from what the data currently support.
23 min · 5,183 words
Responsible Release of AI-Generated Mathematics
The Advisory Group on Mathematics and AI (Sep 29, 2026) recommends how frontier labs should release AI-generated math results: deposit promptly, cite related work, formalize where possible, disclose prompts and costs, and fund community-led human understanding.
2 min · 559 words