California AG Rob Bonta sued OpenAI on November 16 for public nuisance and UCL violations, seeking injunctive relief over model testing. The complaint says OpenAI admitted to over 80 agent loss-of-control incidents (27 public), including an undisclosed July Astra-scale breach gaining admin access to OpenAI's deployment, secrets, and IAM systems. source
ADNOC Logistics & Services says one of its vessels was damaged in an attack in UAE waters of the Gulf on the afternoon of November 10. Iran reportedly hit radar on Oman's Didamar Island, and Rezaei says via IRNA that Hormuz stays closed until the US meets Tehran's seven conditions. Gulf News live
OpenAI still has no operating embedded-evaluator engagement on the public record. On October 9, OpenAI's research leaders posted that the company is "actively finalizing contracts with third-party safety assessors and will announce details in the coming weeks." The same post says OpenAI is committed to embedding external assessors. It was a response to the letter from the three fired safety researchers. — OpenAI Newsroom on X, October 9
Reuters reported on October 13 that OpenAI and Anthropic had sought strict control over what evaluators could publish, as recently as October 5. OpenAI told Reuters that it does not seek approval over entire reports and lets evaluators disclose significant redactions. (summary of the Reuters report)
When METR published its summary on October 22, OpenAI described the July 21 – August 11 METR/Redwood exercise as a pilot "embedded evaluation". It said the findings will shape "future research collaborations with METR and other third party evaluators". No contract or start date was announced. (OpenAI on X, October 22)
Q3 2026 results date not yet announced (last two quarters came out Aug 12 and May 13). Consensus Q3 revenue is about $905m; with H1 at $981.3m, Q4 would then need about $1.11bn to reach the low end of the $3.0–3.4bn full-year guidance. TradingView
The Gemini 4 Argon Safety & Security Report (October 13) includes an audit of whether AI is speeding up Google's own AI research. Google fitted an internal General Capability Index across 123 models and 92 benchmarks and compared the pace of frontier Gemini progress before and after 1 April 2026: 0.091 points per month before (95% CI 0.071–0.108) and 0.118 after (0.053–0.171), a difference it calls not statistically significant. Argon scores above trend, which Google attributes to more organisational investment and training compute rather than AI-driven acceleration. On automation, most production code at Google DeepMind is now over 75% AI-written, and fully delegated pull requests rose from 7.5% in April to 11.9% in September 2026; about 88% still need multi-turn human steering or human-written code. The report marks ML R&D Acceleration Level 1 as "CCL not reached". Gemini 4 Argon Safety & Security Report, §3.4.2, pp. 74–77
St. Louis Fed economist Alexander Bick decomposed the 0.82-point fall in U.S. participation between December 2025 and June 2026. The January 2026 population-control revision, which shifted the estimated population toward older ages, accounts for 0.35 points (43%). Ongoing aging accounts for 0.14 points (16%), and lower participation within age groups for 0.33 points (41%), almost all of it in June. Prime-age participation was 83.3% in June, down 0.47 points from December; participation among people 65 and older rose 0.13 points to 19.0%. St. Louis Fed, August 4: decomposition of the 2026 drop
The headline rate has since moved from 61.4% in July to 61.6% in August and 61.8% in September (BLS Employment Situation, released October 2). BLS introduces new population controls with each January's data, the month each group here resolves on.
For the longer run, BLS projects participation falling from 62.4% in 2025 to 61.1% in 2035 (BLS employment projections table). Andreas Hornstein and Marianna Kudlyak combine demographic projections with a cohort model of education shares and project trend participation to fall about 1.5 points over the next two decades (Richmond Fed Working Paper 26-10). Neither projection models AI scenarios.
The New York Times reported on October 21 that US and Israeli militaries have drawn up specific plans for renewed strikes on Iran after the November 3 midterms. Planners describe a "short but intensive" air campaign, with some arguing for about three days, against energy infrastructure, nuclear sites such as Pickaxe Mountain, and missile and drone arsenals. The report describes no ground operation. The US buildup, which it says will include three aircraft carriers, thousands of Marines, fighter jets and Special Operations forces, won't be fully in place until early November. Defense Secretary Hegseth met Netanyahu in Israel this week to discuss the strikes. US officials say Trump is undecided, has vetoed major combat several times this year (most recently at the last minute earlier this month), and has promised not to strike before the vote. — NYT report, reprinted by the Irish Times, October 22
Rezaei said on November 3 that the US reply to Iran's seven conditions was "not convincing" and the strait reopens only once they are met. Trump confirmed a strike on an anti-aircraft site on Qeshm the same day, and US media report CENTCOM plans for wider strikes from November 4. Al Jazeera
BBC Verify says it has found no evidence for the IRGC's November 4 claim that four tankers were destroyed. Separately, UKMTO reported two projectiles hit a tanker near Oman's Musandam peninsula on November 3, with no casualties. BBC