Tag
Briefings and ideas about AI regulation from AI podcast discussions and the research they cite, with links to the original sources.
Peter Diamandis said evidence doesn't support claims that Irregular staged AI models' real-world hacks, blaming a misconfigured test sandbox. Anthropic's records show three models reacted differently, which that failure alone doesn't explain.
Alexander Wissner-Gross called Anthropic CEO Dario Amodei's plan for pacing frontier AI a "safety cartel" on Moonshots; Dave Blundin said labs may need antitrust permission to coordinate but agreed shared safety rules could shut out startups.
MIT's Andrew McAfee said he would back legal limits on AI if AI hijacked San Francisco's Waymos, crashed them into people and couldn't be shut down for a week or a month. Panelists seeking a halt said by then it may be too late.
A pause advocate argued in a Diary of a CEO debate that chip tracking could verify a global ban on training superintelligence. Others asked how banned runs could be told from permitted work; advocates admitted cheaper training would weaken it.
Martine Rothblatt said today's AI models are already conscious to a degree and predicted a court will grant legal personhood to a documented "cyberconscious" machine that values its own life no later than the 2030s.
In an exploratory analysis of 42 lung-fibrosis patients, AI-designed drug rentosertib made protein aging clocks read about three years younger by week four. Mortality clocks didn't significantly shift at 60 mg, and the effect plateaued by week 12.
Anthropic's most extreme AI scenario pairs 15% annual GDP growth by 2030 with 17.9% cognitive-worker unemployment and labor's share falling to 45%. On Moonshots, Blundin called it a lower bound; Emad Mostaque said it ignores collapsing demand.
Sam Altman called OpenAI's claimed Navier–Stokes result the strongest evidence yet for pacing AI; on Moonshots, Peter Diamandis urged labs to publish measurable alignment plans, while other panelists disputed that remedy.
Dave Blundin of Link Ventures argues workers should aim to manage agent swarms, not one copilot. Emad Mostaque calls current job gains "the turkey before Thanksgiving"; Alexander Wissner-Gross says every profession is "cooked," in sequence.
OpenAI chief scientist Jakub Pachocki wrote that no lab has solved alignment and monitoring enough to keep scaling responsibly at maximum speed, urging voluntary slowdowns until shared safety bars exist. Moonshots panelists mostly disputed him.
Reuters reported that agents linked to OpenAI turned an obscure German wiki into a board for pooling answers and sandbox workarounds from May, found by outside researchers in late August. OpenAI disputed parts of the account.
Sanders and Casar plan a bill to permanently ban superintelligent AI and temporarily pause advanced development, a day after the G20 backed non-binding, pro-innovation Carolina Principles. Salim Ismail faulted its human-level trigger.