Updated
Updated
Showing low-relevance items too. Hide low-relevance items
Mike Knoop@mikeknoopAI score44AIMike Knoop notes that a verification of the roughly 27B-parameter model is notable because it is about as large as fits within the official ARC Prize Kaggle competition runtime. ARC Prize reports Qwen3.8-27B from Alibaba's Qwen team scored 42.4% on ARC-AGI v2 at $0.45 per task and 87.5% on v1 at $0.22 per task.
ARC Prize@arcprizeAI score22AIARC Prize has published full ARC-AGI results for Alibaba's Qwen3.8-27B, with the testing run hosted by Baseten. The post links the public leaderboard, the open-source benchmarking repository for reproducing the results, and the testing policy.
Odyssey@odysseymlAI score30AIOdyssey introduces PROWL-2, a system in which agents and their world model improve through recursive learning. The post says agents expose errors in imagination, and repairing those errors enables further learning. Odyssey frames this open-ended learning as a critical step toward superintelligence.
Odyssey@odysseymlAI score26AIOdyssey introduces PROWL-2, a recursive loop that delivers up to 91% relative gains over the StarCraft world-model baseline. The post also reports stronger robot coordination in simulation.
Google Gemma@googlegemmaAI score54AIGoogle Gemma relays a StudentBench study reporting that AI tutors matched expert human tutors on immediate GRE learning gains. The author reports 2,383 students and a cost of 7 cents per AI tutor hour versus $75 for an expert human hour. The post also says the top AI tutor beat expert human tutors on average in 5 of 7 academic topics, and that the data and paper are publicly available.
Google Gemma@googlegemmaAI score35AINew research finds AI tutoring delivers immediate GRE learning gains comparable to expert human tutors, with Gemma 4 31B performing best. The post presents the findings as a way for educators to scale their impact and make guidance more accessible.
Goodfire@GoodfireAIAI score38AIGoodfire reports that its method catches more unsafe biological requests than frontier model safeguards while dramatically reducing false positives. The claim is illustrated by a plot in the first tweet of the thread.
Goodfire@GoodfireAIAI score29AIGoodfire built monitors that let AI agents perform more biology work while flagging dual-use risks. The monitors reportedly outperform frontier model safeguards, with fewer refusals on dual-use tasks, and run fast and in real time while staying robust to adversarial attacks.
AIGoodfire Research developed sequence-aware monitors using protein language model embeddings to flag concerning biological sequences in dual-use AI agent tasks. On a custom benchmark, the monitors outperformed frontier model safeguards with fewer refusals on benign requests, and they held up better against paraphrasing and fragmentation attacks. The paraphrase results rely on in-silico estimates and do not establish whether the redesigned proteins keep biological activity, and the monitors run in milliseconds per sequence.
Why it matters: The post gives a concrete benchmark setup and fragmentation results, showing how sequence embeddings can separate dual-use biology requests that task-based safeguards handle poorly.
Prime Intellect@PrimeIntellectAI score34AIPrime Intellect reports that after about 100 GRPO steps on Hosted Training, Qwen3.6's reward on held-out problems rose from 0.127 to 0.361, a 2.8x gain. Qwen3.5, trained the same way, reached 0.356, suggesting the method works across model families. Both post-trained models finished well ahead of other open models and narrowed the gap to Claude Opus 4.8, with Qwen3.6 activating only 3B parameters per token.
Zyphra@ZyphraAIAI score26AIZyphra published a paper and blog explaining how local mixing encodes relative position in global NoPE attention models. The work, titled "How Local Mixing Encodes Relative Position in Global NoPE Attention," is available on arXiv and on Zyphra's website.
Zyphra@ZyphraAIAI score22AIModels using Kimi Delta Attention show a recency bias, as the mechanism controlling how much earlier information is kept shapes memory. As new information mixes into that memory, nearby words share more information, which gives the model clues about how far apart words are.
Zyphra@ZyphraAIAI score22AIZyphra derives a mathematical theory showing how local layers produce recency bias that propagates through the residual stream, norms, and MLPs into NoPE attention logits. The authors validate the theory on both randomly initialized and trained networks.
Zyphra@ZyphraAIAI score34AIIn Zyphra's experiments, models with smaller context windows predicted text better while using less training compute. Zyphra believes the stronger recency bias induced by smaller windows outweighs the reduced compute benefit.
Zyphra@ZyphraAIAI score23AIHybrid NoPE models combine sliding window attention or recurrent layers, which focus on nearby words, with global attention layers that use no positional encoding (NoPE). The post notes that NoPE layers receive no positional information yet can still learn long-range dependencies, and raises the question of how this works.
Zyphra@ZyphraAIAI score13AIZyphra says that mixing information within overlapping neighboring windows makes nearby words carry similar information inside a model. This creates a built-in clue about how far apart words are, even before training begins, which the post calls recency bias.
Zyphra@ZyphraAIAI score38AIZyphra Research explains how language models track word order without explicitly encoding position in attention. The post says local memory layers that read nearby words help global attention layers preserve sequence information. The source is a short teaser thread, so no further technical details are given.
Alexander Doria@DorialexanderAI score54AIThe SYNTH paper, titled It's All Training, presents a fully synthetic single-stage pipeline for training workable reasoning models with high data efficiency. The authors argue this approach does not separate training into pretraining, mid-training, or post-training stages. The image shows the paper's abstract, which describes a pipeline built from a 58,000-article Wikipedia-based synthetic corpus and models named Baguettotron-600M and Baguettotron-MoE.
Sara Hooker@sarahookrAI score22AISara Hooker shared a full technical report on a method for creating datasets from zero seed data, linked via alphaXiv. She also pointed readers to an interactive tool at adaptionlabs.ai where users can begin inventing datasets.
Sara Hooker@sarahookrAI score35AICohere's Sara Hooker announced the release of Invent a Dataset, along with a technical report addressing how to build a training set for a new capability with zero starting data. The work targets post-training a model when no data exists, a hard setting for frontier AI development.
AIAmazon Science describes a graph-centric approach in which a network digital twin graph and cascaded graph algorithms, orchestrated by an agentic AI layer, identify root causes in complex network failures. The approach was demonstrated with NTT DOCOMO at the Mobile World Conference, achieving root cause analysis in minutes on commercial networks. The article traces how graphs evolved from topology models to active reasoning substrates for agents.
AIUnder equal time budgets and the same frontier LLM backbone, a single session of a minimal-harness coding agent with read, write, and bash primitives matched open-source state-of-the-art autonomous machine learning engineering harnesses. Apple researchers found the added orchestration and retrieval machinery redundant in large-scale ablation studies, pointing to the backbone model as the main driver of performance. They conclude that hand-crafted harnesses around strong models yield poor returns on current MLE benchmarks.
AIApple researchers introduced RLTL;DR, a reinforcement learning method in which an agent writes its own one-line insight after each failed attempt and learns to map tasks to those insights. On challenging tool-calling and coding datasets filtered to Pass@128 = 0, standard GRPO training of a Qwen 3.5 9B Thinking policy stayed at 0% to 1% Pass@1, while RLTL;DR reached 14–31% with insights in context and 12–13% without them at evaluation. A compact variant, SFTL;DR, trained on just 4k task-insight tuples recovered nearly the full performance of RLTL;DR.
Perplexity@perplexity_aiAI score23AIPerplexity says context-bench, a context-aware retrieval benchmark created and privately held by turbopuffer, has 2,099 queries and 38,894 documents. Perplexity submitted it for blind evaluation, with queries and capabilities inspired by turbopuffer customer conversations.
Perplexity@perplexity_aiAI score20AIPerplexity overcomes gold-chunk supervision limits by distilling relevance from its query-aware context compression model. The model scores every document token against the query, and those scores, aggregated into chunk-level targets, train the embedder to retrieve answer and supporting chunks.
Perplexity@perplexity_aiAI score25AIRetrieval systems that split long documents into chunks lose surrounding context. Contextual embedding models address this by encoding the entire document once and pooling chunk vectors afterward. They are usually trained using one gold chunk per query.
Demis Hassabis@demishassabisAI score62AIGoogle DeepMind reports that AI-designed proteins can be synthesized and watermarked using its new SynthID Bio method, published in Nature. The team says the work is a step toward biosecurity in AI-driven biology and is open-sourcing the SynthID Bio tools for the research community.
Nathan Lambert@natolambertAI score22AINathan Lambert's latest Interconnects plot tracks daily tokens processed by leading open model inference providers. The figures come from public disclosures by Together, Baseten, and Fireworks, plus the OpenRouter API. He says he underestimated OpenRouter's growth.
Ant Ling@AntLingAGIAI score38AILing-3.1-flash built a Lua-to-x86-64 ELF compiler from scratch in about 17 hours, passing 178 of 182 tests for 97.8%. That is within 1.2 percentage points of the 99.0% shown for Claude Fable 5 and above GLM-5.3-Flash at 95.9%.
Ant Ling@AntLingAGIAI score22AILing-3.1-flash ranks #2 in the Mobile App (react native) category on Design Arena's Open Weights leaderboard, with 1,207 Elo. It also ranks #4 in SVG with 1,271 Elo among models added in the last 30 days.
Microsoft Research@MSFTResearchAI score29AIMicrosoft Research has developed a machine learning system that predicts where extreme space-weather events are likely to damage power systems 30-60 minutes before a storm arrives. Such storms can also degrade GPS accuracy and satellite operations, so advance warning could help operators prepare.
AIMicrosoft Research intern-developed machine learning pipeline forecasts location-specific geomagnetic risk for 66,935 substations in the continental United States. It combines solar-wind observations, AE and Dst forecasts, geological conductivity and grid data to estimate risk 30 to 60 minutes ahead. The pipeline detected nearly 80% of major space-weather events during the evaluation period.
Liquid AI@liquidaiAI score42AILiquid AI and InSilicoMeds released LongevityBench, an aging benchmark with 17 tasks spanning clinical records, DNA methylation, transcriptomics, proteomics, and genetics. On several tasks, Liquid AI's compact LFMs outperformed every frontier model the team evaluated. The team plans to present the work to the longevity research community at ARDD this week.
Tencent Hy@TencentHunyuanAI score62AIResearchers from Tencent Hy, Fudan University, and Tsinghua University released ExplorationBench, a benchmark that tests whether AI systems can discover hidden rules in executable Alien World sandboxes. Across 10 frontier systems, getting feedback from experiments outperformed thinking alone, with the best run reaching 89.0% after four rounds. The authors note that rankings barely transfer between the two worlds, and the code is listed as coming soon.
OpenBMB@OpenBMBAI score42AIOpenBMB introduces Diffusion Reward Models (DRM), which learn the full reward distribution of human preferences instead of collapsing them into one scalar score. The approach preserves disagreement and uncertainty, enabling distribution-aware Best-of-N ranking and a new test-time scaling axis by sampling more reward outputs. DRM also improves downstream policy performance over scalar reward baselines when used as the reward in RLHF, according to the post.
Yandex Research@YandexResearchAI score60AIYandex Research says it is releasing AsyncLLM, a framework that lets pretrained LLMs observe, reason, and act concurrently with no additional training. The paper, code, and demos are published on Hugging Face, GitHub, and the project website.
AIAnthropic's research rates how well present-day robots can perform US job tasks, finding they can do 74% of physical tasks, or 34% of working hours, mostly in limited settings. Robots are cost-competitive for only 0.3% of job tasks, and at a 3% annual price decline it would take about 40 years to reach 10%. The report also finds robot-exposed jobs tend to pay less and be more physically demanding than LLM-exposed jobs.
Why it matters: The report separates current robot capability from cost, showing that physical automation is technically broad but economically narrow for now.
Jerry Liu@jerryjliu0AI score20AIJerry Liu says Jev, a System One model, outperformed other open-source classifiers and document-specific models on orientation detection, language detection, classification, and splitting. The benchmark measured accuracy, cost, and latency across these fast document decisions, with Jev leading most comparisons. The benchmark code is available in the run-llama/jev_vs_oss repository.
Jerry Liu@jerryjliu0AI score22AIJerry Liu benchmarked gpt-6.1 sol on document OCR tasks and found a sizable increase in table parsing and reading order over gpt-6 sol from a week earlier. Its table parsing is similar to gpt-6 astra. He noted frontier models still cost roughly an order of magnitude more than cost-effective document parsing solutions, leaving room to improve the premium end above 1c per page.
AINumerical differences between a rollout engine and a trainer can make reinforcement learning collapse even when algorithm and data stay identical. In a GLM 5.2 experiment, reward fell from about 0.9 to under 0.2 around step 20 without alignment, while aligned numerics kept reward stable over 25 steps. A Qwen3.5-MoE investigation traced a significant mismatch to how expert outputs were combined, and router replay alone was judged insufficient.