Smart search ranks by meaning as well as keywords (one row per story, last 45 days).
Simon Willison used GPT-6 Astra (medium) in ChatGPT Work to build an animated D3 transition between Mercator and Equal Earth map projections.
Willison built an animated transition between the Mercator and Equal Earth map projections using D3. The tool was generated by GPT-6 Astra (medium) in ChatGPT Work. Equal Earth is a projection recently voted on at the UN. The post is a vibe-coding demonstration rather than a security or major model event.
Gavel reads native skill-routing signals from a frozen LLM's forward passes with two linear maps, beating retrieve-and-rerank pipelines by up to 21.9 points on Qwen3-32B.
Gavel (Glance And Verdict from a frozen LLM) elicits skill routing from a frozen agent LLM using two trained linear maps that read mid-layer states, keeping all skill text out of context. A glance step scores the full library against compact per-skill banks built in one forward pass at installation; a verdict step resumes shortlisted skills' forward passes and fuses likelihood and yes/no judgments as a product of experts. It transfers zero-shot to three public benchmarks plus SkillTraj, a new benchmark of 372 simulated agent trajectories. On Qwen3-32B it beats progressive disclosure and retrieve-and-rerank pipelines adding 1.2B–16B external parameters by up to 13.4 points on written tasks and 21.9 when skills are needed mid-rollout.
OpenVDN releases VDN-H3, an open hybrid-attention video model on MiniMax H3 that renders a 14.4-second 768p clip in 11.23 seconds on 8 B200 GPUs.
VDN-Minimax-H3 (VDN-H3) adds a frame-wise linear attention branch plus two LoRA adapters to MiniMax H3, distilled into 8-step and 50-step variants. It generates 768p, 14.4-second clips in 11.23 seconds on 8 B200 GPUs (90.5 seconds on one H200) using 8 denoising steps. Weights (about 82 GB total, including the 72 GB H3 base), the optimized inference stack, and training code are fully open-source under the MiniMax H3 Community License, which excludes the EU, UK, Korea, and US.
Unit 42 analyzes an undocumented Upatre downloader variant with VM detection via process hashing, packed code, disabled Windows defenses and Namecoin .bit C2 domains.
Unit 42 analyzed an Upatre downloader variant compiled in December 2016 that went largely undetected by automated systems, featuring heavy code flow obscuration, on-demand decryption of network communications, and novel virtual machine detection. The sample enumerates running processes, computes CRC32 hashes XORed with a hard-coded key, and sleeps if analysis-related processes such as vmtoolsd.exe or python.exe are found. It masquerades with Google Chrome icons, disables Windows Defender, Firewall and other security services, injects code into msiexec.exe, and resolves .bit Namecoin domains like bookreader[.]bit via hardcoded OpenNIC DNS servers over TCP.
Community fine-tune Minimax-h3_Singularity enhances MiniMax-H3 video generation with HDR quality, distant face restoration, and improved motion, trending #22 on Hugging Face.
Minimax-h3_Singularity is a community fusion fine-tune of the MiniMax-H3 multimodal video generation model, built from multiple checkpoints and refined with pruning and weight optimization. It supports Text-to-Video, Image-to-Video, Reference-to-Video, and Video-to-Video workflows in ComfyUI, and claims improvements in HDR clarity, distant face restoration, motion fluidity, and fantasy VFX. The authors recommend pairing it with the minimax_h3_ref2v_turbo_4step_v0.1 LoRA for four-step accelerated inference, and an online demo is available via RunningHub.
vLLM benchmarks speculative decoding on AMD Instinct MI300X and MI355X GPUs across five drafting methods including EAGLE-3 and native MTP.
The vLLM project documents draft-and-verify speculative decoding support for AMD GPUs via ROCm, comparing native MTP, Gemma 4 MTP, EAGLE-3, DFlash, and DSpark drafting approaches. Output-token throughput effects varied with drafting method, proposal length, model family, draft checkpoint, workload, and acceptance behavior. The post also covers how to enable each method plus practical tuning and observability considerations.
CoVeR, a training-free coverage-based token pruner, preserves 93.5% of VLM 3D-reasoning performance using only about 8% of visual tokens.
Researchers introduce CoVeR, a deterministic, training-free selector that chooses visual tokens to cover every region of a multi-view 3D scene using only token coordinates. Unlike learned-importance and voxelization pruners, it enforces an exact per-scene token budget, avoids saturation plateaus, and prevents near-duplicate selections. Experiments across four vision-language models show it surpasses prior state of the art by 3.9 percentage points on average across three 3D reasoning benchmarks.
LandingAI shipped Agentic Document Extraction Gen2 with DPT-3 Pro and DPT-3 Verity parsing models, adding usage-based billing, block-tree outputs, and word-level grounding.
LandingAI has generally released Agentic Document Extraction Gen2, rebuilt around two parsing models: DPT-3 Verity for deterministic transcription of digital documents with per-word bounding boxes and confidence scores, and DPT-3 Pro for layout-aware parsing of scans, handwriting, non-Latin scripts, and LaTeX math. Billing changes from a flat 3 credits per page to a page-plus-output-character model (Pro: 1 credit/page plus 0.5 credits per 1,000 output characters on priority; Verity: 0.3 plus 0.2), with an asynchronous standard tier at 0.5x price and vendor-claimed 25-80% cost reductions. Parse v2 returns a document-page-block tree with semantic IDs, normalized bounding boxes, and line- or word-level atomic grounding, replacing flat chunks; Gen1 client code will not run against Gen2 endpoints. Deployment options include US/EU cloud, VPCs on AWS, Azure, and Google Cloud, Snowflake, and air-gapped on-premises environments, with automated model routing planned for fall 2026.
A review paper frames on-policy self-distillation collapse as governed by three levers: token weighting, privileged information, and guidance decay.
The paper critically reviews On-Policy Self-Distillation (OPSD), where a language model trains on its own generations scored token-by-token by a teacher conditioned on privileged information such as reference solutions or environment feedback. It identifies collapse, the progressive narrowing of producible reasoning paths, as the dominant failure mode and analyzes it through three levers: signal weighting, the nature of privileged information, and teacher dynamics. The review is restricted to mathematical reasoning, reports no new experiments, and offers a shared vocabulary separating settled findings from disputed ones.
A GitHub project streams Moonshot's 2.8T-parameter Kimi K3 from four SSDs to run at 1 token/s on a MacBook Pro.
A GitHub repository (argonautlabsai/deltafin) demonstrates running Moonshot AI's Kimi K3, a 2.8-trillion-parameter model, on a MacBook Pro by streaming its weights from four SSDs at 1 token per second. The project drew 55 points and 22 comments on Hacker News, highlighting consumer-hardware inference for extremely large models.
VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.
VDiff-Bench is a multiple-choice benchmark of 1,756 four-way questions over image pairs covering 10 change categories including position, motion, color, texture, OCR/text and illumination, with curated hard negatives. Evaluation of 11 state-of-the-art open- and closed-source MLLMs shows fine-grained visual comparison remains brittle: 7-8B-scale open-source models score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture. Notably, Grok 4.3 shows a sharp performance drop on noise and texture differences, falling behind large open-source models like Kimi K2.5 and K3.
M-A-P released YuE2-3B, an open music generation model that outperforms Suno v5 on WildSongBench and runs locally on a 24GB GPU.
The M-A-P (multimodal-art-projection) team released YuE2-3B, an open-weights music generation model that turns lyrics and a style prompt into full songs with vocals and accompaniment. It uses an AR-NAR Mixture-of-Transformers backbone with symbolic planning and flow matching through a VAE, and supports editable scores (melody and chords, including ABC notation) plus agentic editing workflows. On 192 WildSongBench prompts it reports a SongBench average of 6.9632 (best-of-8) versus 6.8721 for Suno v5, claimed as state of the art among evaluated open and proprietary models. It runs 48 kHz stereo inference locally on a single 24GB NVIDIA GPU without quantization, with companion releases including YuE2-Vae, MERT-v2 encoders, the WildSongBench dataset, and SheetSage2.
Z.ai released GLM-5.3, a ~750B-parameter model with frontier agentic coding scores, with open weights on Hugging Face planned in two weeks.
Z.ai announced GLM-5.3, initially available only in its coding plan, with API access and open Hugging Face weights promised within two weeks. The roughly 750B-parameter model, one-third the size of Moonshot AI's Kimi K3, surpasses Kimi K3 on many benchmarks and beats Claude Fable 5 or GPT-5.6-Sol on some, placing it at the frontier of agentic coding benchmarks. GLM-5.3 reuses the GLM-5.2 base model with substantially extended post-training based on more RL environments, more diverse tasks and more compute. The post also analyzes how Chinese labs keep pace with the frontier, arguing release speed matters more than distillation.
A multi-signal pipeline detects LLM hallucinations, reaching F1 0.915 on HaluEval and cutting Qwen2.5-0.5B hallucination rates from 85.5% to 37.7% via DPO.
The paper presents a hallucination detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty, and temperature-scaled calibration. It achieves F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks, with MC Dropout inference raising accuracy to 93.2%. Applying DPO to a Qwen2.5-0.5B generator reduces its hallucination rate from 85.5% to 37.7%, while cross-domain evaluation shows poor general-domain transfer to SciFact (F1 0.52) and PubMedBERT fine-tuning as the strongest adaptation (F1 0.63).
CARDEA, a vision-language model trained only on public data, matches cardiologists on coronary angiography complexity assessment while exposing auditable bounding-box evidence.
CARDEA is a unified large vision-language model serving as the inference core of an end-to-end coronary angiography pipeline from multi-view videos to study-level diagnosis. It was trained on public datasets through visual alignment, self-distilled Chain-of-Box cold start, and reinforcement learning with verifiable rewards encouraging bounding-box reasoning. It reached 0.91 accuracy on dominance classification under domain shift and 0.90 on complexity assessment, comparable to two interventional cardiologists. RLVR raised zero-shot report generation vessel-severity macro-F1 from 0.513 to 0.686, while supervised imitation alone did not.
Fal post-trained MiniMax H3 into a 'Max' variant with 35x-faster inference, enabling faster-than-realtime AI video generation and infinite streams.
Fal post-trained MiniMax's H3 model into a 'Max' variant and optimized it for its in-house inference engine, achieving roughly 35x the speed of the official endpoint. The optimization enables faster-than-realtime video generation, demonstrated by an infinite interactive AI-generated stream productized by levels.io. The roundup also notes Meta Muse Code's general availability with an SDK, open DeepSeek-V4-Flash-Vision-Exp weights, GLM-5.3-Flash's strong agentic cost/performance rankings, and Tencent's 770B-parameter Hy4 Preview MoE with 49B active parameters.
WearableQA benchmark tests LLM health reasoning over longitudinal wearable data; the best of 14 evaluated LLMs reaches 72.9% accuracy.
WearableQA comprises 4,084 ten-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning. Evaluation of 14 proprietary and open-source LLMs shows performance from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.
TempCloze benchmark tests Video-LLMs' temporal reasoning with 1,521 videos, finding temporal alignment is the primary failure mode across 31 models.
TempCloze is a video cloze benchmark in which models must identify the true missing middle clip given the beginning and ending clips, using 1,521 carefully filtered videos from seven sources, mostly long-take and egocentric footage. Distractors are constructed along three dimensions: Semantic, Alignment and Progression, with shared scenes and objects to reduce appearance cues. Evaluation of 10 proprietary and 21 open-source Video-LLMs found Alignment is the primary bottleneck, with models often recognizing plausible semantics and local event progression but struggling with temporal alignment.
An open methodology toolkit measures whether transformer language models contextualize fixed word forms across domains using bridge forms and layer-wise silhouette analysis.
The manual documents an open toolkit built around 'bridge forms' - identical written words recurring across two or more subject domains with a different sense in each - to test whether transformer language models individuate word occurrences by context beyond the embedding layer. It covers declarative specification of bridge forms, Wikipedia corpus acquisition, occurrence localization, layer-wise representation extraction, domain-pairwise silhouette measurement, and visualization, justifying each choice against failure modes such as sense contamination and subword-tokenization misalignment. It is a methodological and implementation reference and reports no empirical results.
StepAudio 3 Gen unifies TTS, voice design, music, and sound effects via discrete autoregressive modeling over RVQ tokens.
StepAudio 3 Gen is a general-purpose audio generation model covering zero-shot TTS, voice design, vocal generation, sound effects, music, vibe speech, and mixed audio in one framework. It uses discrete autoregressive modeling over residual vector quantization (RVQ) tokens rather than the diffusion Transformer paradigm, with a StepAudio Tokenizer representing audio at 12.5 Hz in a shared 16x2048 residual code space. Key design principles include interference-aware progressive pretraining, an RVQ Adaptor for multi-codebook acoustic representations, and shared discrete autoregressive modeling. The model reports state-of-the-art performance on TTS and voice design while retaining strong generation across speech, vocals, sound effects, and music.
Google highlights AI-for-science advances: AlphaGenome Atlas mapping 9 billion genetic variants, WeatherNext 3 weather model, and global health AI tools.
Google detailed AI advances across science and health, including AlphaGenome Atlas, which mapped all 9 billion possible single-letter genetic changes in the human genome and was made openly available. WeatherNext 3 delivers 50% more accurate precipitation forecasts a day or more ahead and is already in products. AlphaFold is used by 4 million researchers in 190 countries, TB chest X-ray screening has processed 25,000+ scans across six nations, and the diabetic retinopathy model has supported 1.15 million screenings. Google also released its AI & Economy ATLAS global usage insights.
Controlled mid-training experiments on Qwen3-8B-Base find each domain has a 10-40% coverage optimum and domain gaps survive alignment SFT.
Using Qwen3-8B-Base (with a 4B replication) across five semantically rule-disjoint KOR-Bench domains, the authors train 30 data allocations spanning the five-domain simplex at five seeds each. All five domains show interior optima in the moderate 10-40% coverage band, and domain gaps persist after a fixed-budget compensatory SFT pass, which raises 116/120 cells yet bridges 0/240 pairs at a 5% threshold. Zero coverage collapses mid-training-only accuracy, though a FineWeb-Edu-only control shows the collapse is partly generic drift. The results argue mid-training data composition requires principled design rather than reliance on later alignment.
A retrospective study found GPT-4 over-flagged emergency department revisit cases while an LLM knowledge-graph screener achieved 83-100% positive predictive value.
In an exploratory retrospective study of 99 emergency department diagnosis pairs from a multihospital health system, clinicians and GPT-4 independently judged whether revisit pairs warranted further assessment. GPT-4 responses correlated poorly with clinicians, flagging 94% of pairs for follow-up, 4.4-13.3 times more than clinicians, though prompt engineering was minimal. An algorithm leveraging an LLM-populated knowledge graph (KGA) achieved 83-100% positive predictive value against at least one clinician rater, suggesting LLM-based screening could broaden revisit quality review without substantially increasing reviewer workload.
WearableQA benchmark introduces 4,084 questions over real longitudinal wearable data, showing 14 LLMs score 19.6-72.9% on health reasoning, far from solved.
WearableQA is a benchmark of 4,084 10-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning, using a dual-grounding framework combining literature and population-validated patterns. Evaluations of 14 proprietary and open-source LLMs show accuracy ranging from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.
Simon Willison's pelican SVG comparison shows GPT-6 Astra producing markedly better images than GPT-5.6 Sol, Terra, and Luna across reasoning levels.
Willison generated pelicans-riding-bicycles SVGs with newly accessed GPT-6 Astra at low through max reasoning levels and rendered them in a comparison grid against GPT-5.6 Sol, Terra, and Luna. Astra's outputs were markedly more coherent, while even the best GPT-5.6-Sol images remained largely abstract shapes. Astra does not support a reasoning=none setting, so all comparisons involved reasoning-enabled runs.
Alissonerdx released a rank-64 LoRA sharpening videos from MiniMax H3 in ComfyUI via guide-latent conditioning, trending #30 on Hugging Face.
Alissonerdx published Minimax-H3-ComfyUI, a repository containing a rank-64 LoRA (minimax_h3_lms_v1.0_r64) that sharpens source videos while keeping them photorealistic. It targets the MiniMax H3 ref2va base model, runs with Comfy-Org's ComfyUI-ready weights, and uses the native MiniMaxH3AddGuide node for aligned guide-latent conditioning. The release ships with a ComfyUI workflow, eight before/after example videos, and an Apache 2.0 license.
Agnes AI releases open-weight Agnes-3.0-Flash Preview, a 33B multimodal model with 262k-token context under Apache 2.0.
Agnes AI released Agnes-3.0-Flash Preview, an open-weights multimodal checkpoint with 33B parameters and a 262,144-token context window under Apache 2.0. The model supports text, image, and video understanding, tool calling, and adjustable reasoning effort. The repo clarifies this preview checkpoint is distinct from the production/API Agnes 3.0 Flash model, which uses a different configuration with a 1M-token context window. Reported reference results include IFBench 74.20 and SciCode 38.08 against peers such as Qwen3.6-35B-A3B, Kimi K2.5, and MiniMax M3.
SAFIRE, an 83K-image fire and smoke benchmark, shows open-source multimodal LLMs average only 61.9% accuracy on safety-critical fire reasoning.
SAFIRE is a large-scale benchmark for fire-smoke understanding in multimodal LLMs with 83K captioned images across 20 scenarios and 193K multiple-choice VQA questions spanning 10 evaluation dimensions from perception to higher-order reasoning. Annotations were built via a GPT-5.4-assisted multi-stage pipeline with MLLM majority voting. Ten open-source MLLMs (8B-38B) average 61.9% accuracy, exposing major gaps in safety-critical reasoning. Adapting vision encoders on 7% of the domain data raises fire-scene classification from 20.1% to 64.5%.
A developer benchmarked 10 model/harness combinations on a Three.js task; Qwen 3.8 27B on OpenCode scored 95.64% fastest at 8m48s.
The author ran an identical Three.js sci-fi hangar build prompt across 10 model/harness combinations and recorded score, tokens, durations, and tool errors. Qwen 3.8 27B x-high on OpenCode achieved 95.64% in 8m48s, the best fast result, while GLM 5.3 Flash Max on OpenCode scored highest at 96.89% in 20m28s. Other runs included GLM 5.3 Flash, Luna 5.6, SOL 5.6, and Astra 6.0 across Codex Open, OMP Open, OpenCode, DSH, and PTC harnesses, with scores ranging from 78.54% to 96.89%.
French BabyLM entry METRON-FR (125M GPT-2, 92.47M words) shows tokenizer artifacts dominate child-scale zero-shot evaluation; proposes standard diagnostics.
METRON-FR is a 125M-parameter GPT-2 pretrained on 92.47M French words, submitted to the BabyLM 2026 Strict track, scoring 85.97% on the native Quebec-French QFrBLiMP benchmark and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE protocol combining French task-data translation with rank-16 LoRA shows relational tasks gain while world-knowledge tasks regress. Bilingual Lexicon Induction reaches p@1 of 68.84%, 18x above chance, and ablations show single-token zero-shot scoring is dominated by tokenizer and template artifacts at child scale.
New framework tests whether LLM-cited explanation factors are necessary or sufficient, finding weak correlation across Claude, GPT, and Gemini models.
An arXiv paper introduces black-box intervention tests measuring whether factors LLMs cite in their explanations are necessary or sufficient for their outputs in agent oversight workflows. Across eight models from the Claude, GPT, and Gemini families, Spearman correlations between cited rankings and measured influence ranged from 0.349-0.354 (advisor recommendation) to 0.431-0.580 (prompt monitoring). Uncited factors scored above the lowest cited factor in up to 57.6% of advisor responses, showing cited top-three factors do not reliably identify the most influential inputs.