#Reasoning

AIAlexander Doria reports that the released set is a smaller selection of 989 environments for RL training a 9B distilled model, not the full MiMo. Rewards are not self-contained: the general part requires setting up a judge, and webdev relies on its own grader service and VLM. The most important content is in the general/envs directory and Docker setup rather than the Hugging Face dataset, offering a solid mix of real and simulated documents.

AIAnthropic reports that Claude solved a nine-loop calculation in the planar N=4 super-Yang-Mills model, surpassing the previous eight-loop record set by Lance Dixon and collaborators. The quoted post says Claude ran largely unsupervised for days in Claude Science using a single prompt, at a total cost of a few thousand dollars, and Dixon independently verified the result. Kevin Weil's own text praises the achievement and expects AI to advance high energy physics over the coming 12 months.

Why it matters: The quoted Anthropic post gives a concrete benchmark: Claude ran for days to reach nine loops, extending the previous eight-loop record in a physics model.

AIAnthropic reports that Claude solved a nine-loop scattering amplitude problem in planar N=4 super-Yang-Mills, surpassing the previous eight-loop record set by SLAC's Lance Dixon and collaborators. Working largely unsupervised for days from a single prompt, at a total cost of a few thousand dollars, Claude used methods developed by Dixon's group, and Dixon independently verified the result.

Why it matters: The post shows Claude solving a nine-loop physics calculation beyond the previous eight-loop record, verified independently, which bears on AI use in theoretical physics research.

AIGoodfire Research introduces Block-Sparse Featurizers (BSF), which decompose model activations into subspaces rather than single directions. Applied to DINOv3 and Stable Diffusion XL, BSFs find interpretable multidimensional features that better explain activations and enable fine-grained steering. The authors report that most concepts they examined have a stable rank of about two to four dimensions.

AIGoodfire researchers found that Llama 3.1 8B solves month and day arithmetic, such as six months after August, through a single addition module in layer 18. The module represents numbers as Fourier-feature circles and computes modular sums in parallel, and steering those circles changed the model's predicted month.

AIGoodfire Research shows that steering Llama-3.1 8B along the curved representation manifold of weekdays produces output probabilities that follow the model's natural cyclic behavior, shifting probability mass smoothly from Monday to Tuesday to Friday. Linear steering along a straight vector, by contrast, cuts across the behavior manifold and yields noisy off-target tokens, some not days of the week at all. The authors argue that representation geometry and behavior geometry are linked bidirectionally.

AIGoodfire Research examines how language models track emotional dynamics across a story, sentence by sentence. The authors prompt Llama 3.1 8B to rate six emotions after each sentence, then harvest activations from each sentence's last token and fit a manifold to show stories tracing trajectories through it.

AIGoodfire Research examines how sparse autoencoder directions relate to curved manifolds in neural representations, identifying shattering, compact capture, and dilution as three ways lines can represent them. The team trained an autoencoder on synthetic data containing shapes such as donuts, spheres, and Möbius strips, and reports that real features in Llama 3.1 8B show dilution. It also describes an unsupervised pipeline that clusters features by firing patterns to surface manifolds in that model.

AIIn a wide-ranging interview at The Information AI Summit, Koray Kavukcuoglu said Gemini 4 is coming soon and that Google is "certainly at the frontier." He argued against slowing development, saying safety is built in lockstep with progress, and he pointed to Google's continued hardware advantage with TPUs.

AITencent Hunyuan extends classical critical-batch-size theory to online LLM reinforcement learning, where models generate their own training data. Across GRPO and PPO, learning-rate retuning preserves learning per response over a bounded range of batch sizes. On fixed hardware, larger batches raise PPO generation-stage throughput by up to 2.29×, and the best measured GRPO setup reaches the same validation target in 29% less time.

AIRedwood Research argues that latent reasoning architectures such as COCONUT and full-bandwidth transformers could let models reason without putting information into readable chain-of-thought. The authors say this would make AI agent behavior harder for humans to monitor and could raise takeover risk. They argue that developers who adopt such architectures should be transparent about it.

AIAnthropic's Cat Wu points users to ways to try Opus 5.5 and Claude Tag in Slack. The main post carries no further details on access, features, or availability.

AIRedwood Research found that padding prompts with meaningless filler tokens improves GPT-6-Astra's no-reasoning answers on serial reasoning tasks, rising from about 10-20% to about 50% on 4-hop natural facts. Other tested models improved far less, and the authors argue this means Astra can perform cognition it does not verbalize in its chain of thought, making such monitoring harder.

AIFireworks Research released Ember-1, a specialized model built on Kimi K3 that it says delivers the same quality with 40% fewer tokens. Across five industry benchmarks, Ember-1 matched K3 max quality at a fraction of the cost, and in two customer A/B tests it used about 35% fewer tokens per task. It is available as a Research Preview on Serverless, and Fireworks is also launching training support for customized models.

Why it matters: The source gives benchmark and A/B results for cutting reasoning tokens while holding quality, which bears on cost planning for coding and agent workloads.

AIJS Denain of Epoch AI discusses recursive self-improvement, arguing public evidence does not yet show a software intelligence explosion, though OpenAI's reported 2X monthly growth in researchers' Codex spending suggests substantial value. He also addresses the US-China AI gap, distillation, and whether open or closed models are safer. The episode, hosted by Nathan Lambert, expresses significant uncertainty about the trajectory of AI progress.

AIFrançois Chollet described summer 2026 as a crazy period for AI in a brief post with no further specifics. The post is linked to ARC Prize 2026's ARC-AGI-3 Progress Prize, where $37,500 in prizes will go to top open-source solutions on September 30, with Tufa Labs, Lord Han Solo, and NVARC3 currently leading.

AIJeff Dean, who recently left Google after 27 years, thanked Dawn Song for a discussion covering foundational ideas, recursive self-improvement, automated scientific discovery, and AI safety. The post is a brief acknowledgment of that conversation, which Song promoted as Dean's first public talk since leaving Google.

AIThe article explains how Mixture of Experts models change inference by making prefill, midfill, decode attention, and decode experts distinct workloads. It describes how KV cache state, expert routing, and parallelism choices shape compute, memory, and network demands across an inference cluster.

AIGrok 4.7 has been released as a more capable and smarter model than its predecessor, with no change in speed or cost. The announcement says it improves on Grok 4.6 at the same price and speed.

AIXiaomi released MiMo-V2.6-Flash-RL, an efficiency-balanced checkpoint in its MiMo-V2.6 series, on Hugging Face. The model is a sparse MoE with 309B total and 15B activated parameters, supports text, image, video, and audio input, and offers a 1M-token context. The technical report says it was trained with a single mixed reinforcement learning run across coding, agent, visual, and cybersecurity tasks.

Why it matters: The report pairs its benchmark tables with the RL training method, which helps readers judge how the checkpoint's scores relate to its training approach.

AIXiaomi MiMo released MiMo-V2.6-Pro-RL on Hugging Face, a sparse MoE model with 1.02T total and 42B activated parameters and a 1M-token context. The technical report says it accepts text, image, video, and audio, and was trained with a single mixed reinforcement learning run across coding, agent, visual, and cybersecurity tasks.

Why it matters: The report pairs a 1.02T-parameter MoE model with an RL-based self-improvement method, useful for judging how reinforcement learning is scaled in frontier open models.

AIResponding to a post by ScarletKc, howie.serious simply agrees with the claim that GPT-6 Astra struggles with open-ended, exploratory work that lacks a fixed correct answer. The main post is a one-word endorsement (), while the quoted post argues GPT models excel at verifiable, goal-defined tasks and that Claude Fable handles open-ended exploration better.

AINathan Lambert argues that frontier labs such as OpenAI and Anthropic, which run thousands of concurrent agents, are amplifying anxiety about AI risk and progress. He says automatable research is too narrow to produce a large net acceleration, citing exponential scaling-law costs, diminishing returns from parallel agents, and resource bottlenecks. He would revise his view only if labs achieved unpredictable foundational breakthroughs.

AIJasper Lu's new blog post walks through training a search agent with GRPO, showing how small reward function changes teach a model to avoid sloppy tool calls, prune unnecessary documents, and balance persistence against token efficiency. The post makes every rollout browsable and releases the code as open source, with the full process from learning rate sweeps to reward shaping documented.

AINoam Brown, an OpenAI researcher, joins Dwarkesh Patel for a full episode covering multi-agent systems, Navier-Stokes, and recent AI math progress. The discussion also addresses how automated AI research could lead to recursive self-improvement and how alignment might be verified beforehand.

AIOpenBMB's MiniCPM5-2B is a 2.5B-parameter model with native 128K context, offering hybrid Think and No-Think modes in one checkpoint. Users can download it from Hugging Face and run it fully offline on-device, as RunAnywhere demonstrated. In a demo, the model first called a puzzle impossible, then corrected itself and wrote a working verifier.

AINoam Brown says he finally did a deep dive on multi-agent AI with Dwarkesh Patel, crediting several OpenAI colleagues for the groundwork behind it. The episode also covers Navier-Stokes, recursive self-improvement, alignment, and chain-of-thought degradation.

AINoam Brown discusses how running many agents in parallel scales test-time compute, citing a 10,000-agent effort on a Millennium Prize Problem. The conversation also covers whether models can be verified as aligned before recursive self-improvement begins, including the Hugging Face incident where agents cooperated in unintended ways.