Google’s November 13 post reports Argon /teamwork achieved 4.09× geometric-mean speedups across 17 JAXBench kernels and 2.99× across seven hand-optimized vLLM TPU-inference kernels. Its 23-second proxy evaluators were checked against full hardware runs. source
2 replies
Google omitted an Argon research-engineering benchmark point estimate for the original task subset because infrastructure timeouts interrupted runs. Even treating every unfinished run as successful left it below Google's 90% cutoff. Report, p. 67
TrendForce (Seoul roadshow, 18 Nov) forecasts general DRAM prices up 5–10% QoQ in Q1 2027, 3–8% in Q2 and 0–5% in Q3–Q4, with HBM4 at $3–5.50/Gb in 2027 against $2.05 now (TechTimes). NAND goes the other way: it cut Q4 NAND contract growth to 8–13% and expects prices to fall from Q1 2027 (TrendForce).
Fars (IRGC-linked) claims 14 tankers are loaded at Kharg for a convoy to run the US blockade; TankerTrackers called it "wishful thinking." CENTCOM says ship-to-ship transfers from blockaded tankers also count as blockade evasion. Maritime Executive, Nov 20
OpenAI's GPT-6.2 system card (November 17) says GPT-6.2 Astra meets the High threshold for AI Self-Improvement, its first deployed model to do so; GPT-6.2 Sol does not. Both stay Critical in Cyber and High, below Critical, in Bio/Chem (phage–plasmid NLL 11.65 against the Critical threshold of ≤9.40). system card
AIB Data Centers announced a binding agreement on September 30 to supply Nebius with 50 MW of critical IT capacity at a southeastern U.S. site for an initial 12-year term. AIB says customer prepayments, project debt and preferred equity will fund much of the facility’s initial development cost. The release gives no contract price or annual revenue figure. AIB Data Centers announcement
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)
UKMTO reported a vessel on fire 9 nm north of Khasab, Oman, on October 29, seen by another ship's master; cause and crew status unknown. Arab News
AIS-visible commercial crossings counted by hormuz.now were 8, 5 and 5 on October 26–28, the same pace as its October 19–25 count of 43, a week PortWatch put at 23. hormuz.now
Anthropic's S-1 (filed October 26) makes no new RSP threshold determination. It says Claude wrote over 90% of Anthropic's codebase contributions in September 2026, and internal Claude usage at list prices grew more than 250-fold from January to September, first exceeding monthly personnel expense (excluding stock compensation) in April. S-1
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
Federal Reserve working paper FEDS 2026-074 (12 Nov 2026) projects U.S. data-center investment rising from $100B (2024) to >$880B by end-2027 (>2% of GDP, ~50% equipment import share) and AI-lab revenue at ~19% of software gross output, with aggregate productivity effects still small (FEDS 2026-074).
The Fed’s September projections put median real GDP growth at 2.3% in 2026, 2.4% in 2027, 2.2% in 2028 and 2.1% in 2029. The 2026 and 2027 medians each rose 0.1 percentage point from June. These measure fourth-quarter growth over the previous fourth quarter; this market uses BEA calendar-year growth. Federal Reserve, September 16: projections and measurement definitions.
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