Federated Conformal RAG (FC-RAG) provides distribution-free coverage for a bandwidth-limited swarm of weak language models, but only at a fixed horizon. We extend it to anytime-valid sequential coverage: validity at every stopping time, preserved under predictable adaptive control (recalibration, per-node bandwidth escalation, distilled-student refresh), at no extra cost in assumptions over fixed-horizon FC-RAG. Naive composition fails because FC-RAG's marginal coverage bound makes the betting e-process a non-supermartingale on adverse calibration draws, and Ville's inequality cannot be invoked. We give Anytime-FC-RAG, a sequential extension built on a summable per-step calibration-deviation budget that converts the marginal bound into a strict conditional bound on a calibration-good event, paired with a truncated betting e-process that is a nonnegative supermartingale on the entire probability space. From these two ingredients, we obtain four guarantees: time-uniform alarm validity $\mathbb{P}(\sup_t E_t \ge 1/δ_e) \le δ_e + δ_{\mathrm{cal}}$, a Hoeffding-stitched cumulative-miscoverage envelope at the same total budget, safety under any predictable controller (recalibration, bandwidth escalation, student refresh), and training-side error propagation across an unbounded sequence of Federated Probe-Logit Distillation (FPLD) refreshes via a summable training budget. As a practical consequence, an adaptive controller that escalates retrieval bandwidth only when the e-process crosses a warning threshold matches the alarm rate of a fixed-high-bandwidth schedule at substantially lower communication cost. Experiments on a GPT-2-small + MiniLM swarm across MMLU, DBpedia, and AG News verify the predicted alarm rate, detection delay, envelope coverage, and $14$-$57\%$ bandwidth savings; the alarm fires when and only when coverage genuinely breaks.

Earlier today, Meta announced that it was testing a new Meta AI chatbot for Threads that would function a lot like Grok on X. Even though the early beta isn't available to most people on the platform yet, a number of Threads users have discovered its not possible to opt out of the feature or block chatbot's the account. While most people aren't able to interact with bot yet -- the initial testing is limited to Malaysia, Saudi Arabia, Mexico, Argentina and Singapore -- the public-facing @ meta.ai account is viewable to everyone on the platform. The account's initial post has been met with a flood of angry replies from users demanding to know why, unlike any other Threads account, there's no option to block it entirely. Some users have even said that they have reported the account for spam, which typically ends with the option to block, only to find out that the block didn't actually go into effect.

Training a language model on data scattered across bandwidth-limited nodes that cannot be centralized is a setting that arises in clinical networks, enterprise knowledge bases, and scientific consortia. We study the regime in which data must remain distributed across nodes, and ask what statistical guarantees are in principle achievable under explicit bandwidth budgets; we aim to characterize what is provably possible, not to demonstrate a deployment-ready system. Existing theory treats either training-time consistency or inference-time calibration in isolation, and none makes bandwidth a first-class statistical parameter. We analyze two protocols, Federated Probe-Logit Distillation (FPLD) for training and Federated Conformal RAG (FC-RAG) for inference, as the analytical vehicles for our results. Our first main result is an explicit high-probability KL-consistency rate for FPLD with simultaneous dependence on node count $K$, per-node sample size $n$, quantization budget $B$, probe-set size $m$, and vocabulary size $V$; bandwidth enters only through an exponentially vanishing quantization term. Our second main result is a distribution-free marginal-coverage bound for FC-RAG, whose novel retrieval-bandwidth slack $Δ_{\mathrm{RAG}} = f_{\max}\sqrt{K^{-2}\sum_i v(B_i)}$ makes per-node retrieval bandwidth a first-class statistical parameter, with arithmetic aggregation across $K$ nodes shrinking the slack as $K^{-1/2}$ in the per-node-uniform regime. A Pinsker-type corollary composes the two bounds into an end-to-end coverage guarantee. Synthetic experiments verify the predicted scaling along the bounds' parameters; small-scale experiments on a GPT-2 testbed illustrate that the qualitative bandwidth-accuracy tradeoff survives on a real language model. A deployment-scale empirical evaluation is out of scope.

Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the inherent stochasticity of LLM outputs and the heterogeneity of benchmark items. Item Response Theory (IRT) offers a principled framework for modeling latent model abilities and item characteristics, but conventional methods are computationally expensive and numerically unstable, limiting large-scale implementations. To address these challenges, we propose an interpretable and scalable framework for LLM evaluation based on the majorization-minimization principle. Our approach reformulates the problem as a sequence of constrained matrix factorization subproblems, enabling stable and efficient parameter estimation with theoretical guarantees for identifiability and convergence. Experiments on synthetic and real-world datasets, including MATH-500 and six Open LLM Leaderboard benchmarks, demonstrate that our method achieves superior scalability and interpretability. It delivers orders-of-magnitude speedups over competing methods while maintaining comparable or even higher estimation accuracy. Our results align with established scaling laws and offer insights into item difficulty and discrimination, informing more principled benchmark design.

Researchers have developed three new antibiotics from scorpion venom and habanero peppers to combat tuberculosis and other drug-resistant pathogens. Researchers from the National Autonomous University of Mexico (UNAM) have identified new ways to combat tuberculosis and reduce bacterial resistance, developing three new antibiotics derived from scorpion venom and habanero peppers. A team led by Lourival Domingos Possani Postay, from the Institute of Biotechnology's Morelos campus, created two drugs that demonstrated efficacy against the bacterium, responsible for tuberculosis, as well as against, a microorganism that in hospital environments can cause various clinical complications, from skin infections to potentially fatal diseases such as pneumonia, meningitis, septicemia, and endocarditis. The antibiotics were derived from the venom of the scorpion, native to the state of Veracruz. The team was able to isolate two colorless molecules called benzoquinones--heterocyclic compounds that do not contain amino acids--from the arachnid's toxin.

I own 20 axolotls - people need to know they're not easy to look after When Emma Honeyfield's daughter Amber asked for an axolotl for her birthday, Emma never imagined it would lead to a collection of 20. The 37-year-old bought her daughter's first axolotl, Stitch, in September and has since fallen in love with their calming nature. Emma said Amber, eight, had always been difficult to buy for, so when she asked for one for her birthday, she couldn't say no. And the family, from Tredegar, Blaenau Gwent, are far from alone in seeking out the amphibians, which are critically endangered and only found in lakes and wetlands in southern Mexico City . The animal's cute, smiling face and appearance in the hugely popular Minecraft and Roblox games has seen an increase in the number of people keeping them as pets.

AI newsletter covers Dairy Queen's automated drive-thru backlash, Meta's 8,000 employee layoffs amid its AI push, and voter concerns about privacy and paychecks.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG . Toyota's CUE7 robot shoots hoops using AI You don't need an SSN to open a credit card: Scammers know that Mexico's climate supercomputer could change forecasting Michael Easter and Gary Brecka discuss the'choice' to live to be 100 'CyberGuy' warns of creepy privacy clauses in smart devices Brian Oliver of Gainesville, Florida, spoke with Kurt CyberGuy Knutsson about losing money to scammers claiming to be with PayPal. NEW You can now listen to Fox News articles! Brian Oliver is retired, sharp and financially savvy enough to have a stock-and-bond portfolio worth hundreds of thousands of dollars. He is not the type of person you picture getting scammed.

Toyota's CUE7 robot sank a free throw at Toyota Arena Tokyo using AI-powered reinforcement learning instead of pre-programmed instructions, marking a shift in how robots are trained.