I Used NYT Cooking’s New AI-Powered Recipe Modifier, and It’s Actually Pretty Good
The New York Times has added a beta feature to its Cooking app that helps readers swap ingredients or adjust recipes to suit their needs. It mostly hits the mark.
AI NEWS JOURNAL
Search AI news
Search headlines, summaries and articles to connect the dots.
Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster
Zyphra released ZYFA, open-source FP8 and BF16 prefill attention kernels for AMD Instinct MI355X. On real model activations, its FP8 kernels run 1.16-1.76x faster than AMD’s AITER, with 62-78% lower error at head dimension 128. The post Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster appeared first on MarkTechPost.
BlockLock: Reproducible LLM Inference with Fixed Batch Geometry
arXiv:2611.06977v1 Announce Type: new Abstract: Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and isolating prefill with fixed-shape decode ({our CoRun-style baseline}) gives up shared prefill compute and pads decode. We present BlockLock, which keeps shared batched prefill and pins only the numerical path of the protected request: it fixes the geometry that the request sees, with {two modes: BlockLock-Rows uses fixed-width rows and retains batched decode of all requests; BlockLock-Pack uses terminal-anchored packing with an isolated dummy segment, then extracts the protected request's KV state for target-only decode. Under a stated per-deployment contract, both modes preserve the target's output bitwise when its companions change.} Across five {dense} models (Qwen3-8B/14B, Llama-3.1-8B-Instruct, and Gemma-3-4B/12B-IT) and three single-GPU deployments (NVIDIA A6000, A100, and H100), we evaluate our approach on both tinyBenchmarks and BFCL{; we also include initial tensor-parallel experiments on two NVIDIA A6000 GPUs. Both modes preserve target sequences and Top20-logit bits in the reported tests.} At equal delivered work, {BlockLock-Rows} reduces latency by 53.5--55.0\% and improves throughput by 115.2--122.2\% relative to vLLM Batch-Invariant; compared with batch-invariant kernels, it needs no custom kernel implementations and constrains only the protected requests.
Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
Google DeepMind has launched Gemini Omni 1.2 Flash, introducing native 15-second video generation, improved reference adherence, stronger consistency across frames, multi-turn conversational editing, more natural speech, and cinematic camera movements. The model is now generally available via the Gemini API and Gemini for business, priced at $0.07 per second for 720p video—30% lower than its predecessor. It supports scalable workflows, including draft generation at lower resolutions, iterative edits, and upscaling to 1080p or 4K. Use cases include product explainers, social ads, virtual try-ons, and branded content, with applications across Google AI Studio, Google Cloud, Google Vids, Flow, the Gemini app, and Google Ads.
Information-Matched Auditing of Conversational Emotion-Shift Forecasting: A Leakage-Safe Evaluation Protocol
arXiv:2611.05895v1 Announce Type: new Abstract: Comparisons in conversational emotion-shift forecasting are easily distorted when a learned model receives rich features but its transition baseline is given a noisy or unavailable current-emotion label, when hyperparameter budgets differ, or when target-turn information enters the representation. We present an information-matched, leakage-safe auditing protocol that closes these gaps with an explicit commitment point, executable causality tests, equal four-configuration validation searches, and seed-dialogue-aware inference. Applying it to six causal model families on four text corpora and two feature-source sensitivity configurations shows that a deployable train-only current-emotion classifier feeding the transition baseline yields a different verdict than an oracle diagnostic where both sides receive gold current emotion. Under the deployable condition, learned models improve over the predicted-label baseline on all four primary corpora; DailyDialog gains are large and survive a 72-comparison Holm correction (best ROC-AUC gain = +0.167, adjusted p=.0144). Under matched gold information, the baseline remains competitive on IEMOCAP and stronger on MELD, while every model retains a large DailyDialog advantage. We additionally report precision-recall AUC, calibration, a strictly utterance-local feature control, same-person self-shift forecasting, and a future-access dose-response test. An eight-item leakage checklist accompanies the protocol. Code, raw seed predictions, and reporting artifacts are available from the corresponding author upon request.
Measuring how AI agents handle everyday wet-lab science
OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.
New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
NVIDIA has introduced four new open-weight checkpoints for its Cosmos 3 model family—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—enabling interactive world simulation and multi-sensor, multi-view driving scene generation. Each model is a post-trained variant of Cosmos 3 Nano with 16B trainable parameters and is based on OpenMDW1.1, allowing commercial and non-commercial use. The checkpoints support applications in robotics and autonomous driving by generating synchronized camera and LiDAR data, enabling streaming simulations, translating simulator controls into photorealistic video, and predicting visual outcomes from robot actions. They are designed to be adapted using custom data and training recipes, with support for offline data generation, causal distillation, and interactive rollouts. Resources include technical reports, demos, and notebooks for inference and adaptation.
A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
Phonon, a small text-to-speech model that runs entirely on the user's device without requiring internet access, has been released with support for English, French, German, Spanish, and Portuguese. Built on the Pocket TTS lineage using flow matching, Phonon achieves high-quality audio in compact sizes (65 MB and 75 MB), with the 31m version licensed under Apache 2.0 for commercial use. It excels in intelligibility and speed, ranking first in German and Spanish on Hugging Face's Open TTS Leaderboard and leading in CPU streaming benchmarks. The model supports voice cloning, custom voices via Gradium Studio, and integrates with Hugging Face Transformers. It is available in multiple formats and backends, including WebAssembly, GPU, and NPU, enabling deployment across phones, laptops, single-board computers, and browsers. Over 200,000 downloads were recorded in its first two weeks, with active developer adoption through tools like ExecuTorch, Micdrop, and Spaces. Future developments include support for additional languages, smaller models, and custom vocabulary fine-tuning.
A Controlled Experimental Evaluation of Configuration and Cache Architecture in LLM Serving Engines
arXiv:2611.05991v1 Announce Type: new Abstract: Multi-agent LLM applications repeat most of their prompt tokens across requests, and serving engines reuse the cached state of shared prefixes. vLLM and SGLang reuse it at different granularities, and benchmarks of their default deployments report large performance gaps, usually credited to the cache. Such comparisons rarely control for other configuration differences. One of them, whether a long prompt is prefilled in chunks, is set by each engine's defaults from the hardware and the release, and it confounds the comparison. We built a reproducible testbed on Kubernetes and a seeded multi-agent workload generator, and compared the two engines under vendor defaults and with chunked prefill matched. SGLang's configuration is the same in both arms, which makes it an internal control across independently provisioned deployments. Under defaults, vLLM's median time to first token is up to 64x SGLang's. Matching one setting removes 78% of the capacity gap where that gap is largest and 30 to 67% of the latency gap. Near saturation the remaining latency gap reflects queue growth. A fluid queue model driven only by a 4.4% throughput shortfall reproduces it, and shows that such a gap scales with the length of the benchmark run. What survives matching is a tail-latency advantage of 2.4 to 6.4x at equal throughput, consistent with cache-aware ordering of waiting requests. We derive six recommendations for comparing serving engines.
Clearing up a robot’s fuzzy memory
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
The Dharma Field Extractor, a 2-billion-parameter model, specializes in extracting specific fields from diverse document types—such as invoices, IDs, and medical forms—into structured JSON format. It outperforms general-purpose frontier LLMs in accuracy and reduces cost by up to 147 times when self-hosted, demonstrating that domain-specialized small models can surpass large general-purpose models on well-defined tasks. The model supports both open extraction (detecting fields without a schema) and schema-directed extraction (returning exact field names and types), with training data spanning English, Brazilian Portuguese, and multilingual documents. Benchmarks show superior F1 scores and valid JSON output across real-world datasets like SROIE and FUNSD, reinforcing the thesis that specialization beats scale for enterprise document processing.
Flipsnack grows product signups with conversion optimization
Flipsnack focused its ChatGPT Ads campaigns on getting people to try its product, growing registrations while lowering the cost per signup.
Prospective Memory for Proactive LLM Agents
arXiv:2611.05731v1 Announce Type: new Abstract: Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions. Proactive agents, however, also require prospective memory: retaining future-directed intentions and realizing them when appropriate opportunities arise, even without explicit requests. Crucially, remembering the right intention does not guarantee acting at the right time: a related observation may call for waiting, while a later cue may make the same intention actionable. Inspired by cognitive theories of human prospective memory, we introduce Pro-Memory, a memory framework that separates maintaining future intentions from deciding when and how to realize them. Pro-Memory preserves pending objectives linked to their supporting evidence, assesses new observations against their original goals and activation conditions, and coordinates appropriate contributions with the agent's ongoing actions. It further updates intention states based on actions actually issued or evidence of resolution, while an experience memory distills feedback from completed episodes into guidance for future decisions. Experiments on two benchmarks spanning delayed-intention tasks and open-ended proactive assistance demonstrate consistent improvements in proactive task performance over representative memory approaches across multiple LLM backbones, while limiting unnecessary interventions.
Verified but Vacuous: Three Failure Surfaces of LLM-Driven Verified Code Generation
arXiv:2611.05590v1 Announce Type: new Abstract: What should ``verified'' mean when evaluating LLM-generated code? Many existing pipelines report a single verification number. We argue this collapses three distinct properties measured in a conditional audit sequence: verifier acceptance (Surface A), \emph{syntactic specification binding (Surface B: does the proof obligation bind to the spec?), and \emph{semantic specification fidelity} (Surface C: does the spec capture the informal requirement?). Two empirical demonstrations show the surfaces separate. \textbf{First ($A \neq B$), via Li@Opus (a same-model reproduction of \citet{li2025dafny}'s Dafny-as-intermediate-representation (IR) pipeline under Claude Opus 4.7) on three Python benchmarks}: it reaches \textbf{99.1\% verifier acceptance} on HumanEval while only \textbf{1.9\%} carry a certificate binding to a spec-defined predicate or function. \textbf{Second ($B \neq C$), via VCG on two Rust benchmarks}: we use VCG (which is our own in-house Dafny-as-intermediate pipeline) on Rust because the Rust target lets us enforce fully-verifiable output (every component ships as a Dafny certificate, ensures-binding gate passing by construction). Even inside that construction, \textbf{11.48\% (MBPP-Rust) and 14.82\% (VeriContest LC slice) of structurally-verified samples still fail hidden tests}. On the LC slice of VeriContest, \textbf{VCG's reported End2End rate is 7.79\% (535/6870).} The cited external rates are 5.51\% (GPT-5.5) and 1.88\% (single-shot Opus 4.7). These give descriptive differences of 2.3 percentage points and 4.14$\times$, respectively; task-budget, repair and harness differences prevent a matched-performance claim.
A thousand fewer paths to root
OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.
Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated Learning
arXiv:2611.03724v1 Announce Type: new Abstract: In receiver-directed federated learning, each site draws a trust boundary. For every source and model component it judges, on its own data, whether the transfer helps (admit), harms (reject) or cannot yet be told (abstain). We ask whether this boundary holds over hundreds of rounds. Our benchmark has a federation of thirteen semi-synthetic sites, an exact oracle for every evaluated transfer, paired seeds, an attack protocol, fourteen methods over 600 rounds and Qwen3-1.7B LoRA sites over 500. The answer depends on which boundary is measured. Across 20 paired CPU seeds, a gate judging against a fixed reference better identified transfers useful relative to the site's starting model. Yet it admitted 29% of transfers harmful to the model the site now has. A gate judging against the current model admitted 2% of harmful transfers on that target in the CPU tier, but missed many transfers useful to the starting model. Two short propositions explain these distinct failures. We also evaluate a held out audit that leaves gate verdicts intact. After training, it decides whether each final model is deployed or the site falls back to local training, and reports admissions that have gone stale. With independent audit data its guarantees hold after any training history. At 600 rounds the audit deployed 65 to 72% of models, none with negative benefit on its target, and kept 98% of the gain. No stale report had the wrong sign in our runs. With 20,000 audit observations, a variance-adaptive bound found 99% of stale transfers that cost at least 0.01 in log loss. A common-target Qwen3 comparison on 60 selected transfers shows the same tension over 100 rounds. With 38% adversarial sites, FedFomo and CS-Gate were the only evaluated methods with positive mean gain in every honest group.
Same Rule, Different Verdicts: Rubric Language and Clause Structure in LLM Judges for Korean Support Dialogues
arXiv:2611.04091v1 Announce Type: new Abstract: Services that operate in Korean often write their evaluation rubrics in Korean and hand them to an LLM judge. We test whether a judge's verdict depends on the language of the rubric and on how a rubric item is phrased. We write 12 criteria for support dialogues in four clause structures (affirmative, negated, conditional, exception) such that two pairs of structures have the same meaning, and we give each item in Korean and in English. Six low-cost models from three providers, plus one reference model, judge 60 translated ESConv dialogues and 144 constructed boundary cases under every combination (51,744 requests across the seven models). The analysis plan was fixed and committed before data collection. Cross-provider agreement is lower with Korean rubrics than with English rubrics (Cohen's kappa 0.687 vs. 0.745; difference -0.058, 95% CI [-0.072,-0.045]). Disagreement concentrates in negated, conditional, and exception items (odds ratio 5.6 relative to affirmative items). A single model changes its verdict between two items with the same meaning in 11-15% of cases. Two hypotheses are not supported: models from the same provider do not agree more than models from different providers, and adding paired examples does not reduce the language gap. We measure consistency only; no human labels are used, and all materials were drafted by an LLM.
ScienceVision: Can AI Observe and Reason Like a Scientist?
arXiv:2611.04087v1 Announce Type: new Abstract: Scientific discovery builds on accurate observations interpreted through domain knowledge and reasoning. For scientific 3D data, this requires understanding structures and spatial relationships, from protein contacts to anatomical organization. Existing multimodal benchmarks largely evaluate text and 2D images, while scientific 3D evaluations vary in representations and protocols across disciplines, limiting cross-disciplinary comparison. To assess these foundational capabilities, we introduce ScienceVision, a cross-domain benchmark for scientific 3D understanding and reasoning through expert-level visual question answering (VQA). We construct 250 questions, with 50 each from Biology, Chemistry, Medical Imaging, Mechanical CAD, and Architecture, through a pipeline combining synthetic question generation with domain-expert review and annotation. Each task pairs a native 3D artifact with a scientific question, a specified response format, and a task-specific reference answer, requiring domain knowledge to be applied to geometric or topological evidence. We evaluate 12 models on the same questions in three settings: visual question answering with native 3D artifacts accessed through an agent harness's file and code-execution tools; the same workflow augmented with expert-inspired viewer inspection and measurement tools exposed through the Model Context Protocol (MCP); and visual question answering from prescribed rendered 2D images using an agent harness. All settings use the same task-specific deterministic final-answer scoring. The inspection environment supports view changes, target isolation, and slice inspection. In this main comparison, the best mean answer score is 0.53 out of 1. Mean scores in the native-artifact workflow without additional MCP tools exceed those in the rendered-image workflow for every model, by 17.2 percentage points on average.
Swapping the Judge Changes the Ranking: A Preregistered Study of Cross-Provider Replication in LLM-Judged System Comparisons
arXiv:2611.04090v1 Announce Type: new Abstract: Practitioners who compare systems with an LLM judge and have no human labels often check a conclusion by repeating it with a judge from another provider. We test how far that check can be trusted. In a preregistered study (with a disclosed post-registration reduction of the judge set), five judge models from three providers re-judged 4,000 Chatbot Arena battles (nine systems, 33 system pairs) that carry human votes, each in both response orders. Agreement with the human vote was low at the verdict level (median Cohen's kappa = 0.22), and system rankings did not survive a change of judge: Kendall's tau with the human ranking ranged from 0.17 to 0.89 (median 0.67), so the preregistered hypothesis that rankings remain stable was not supported. Conclusions replicated by two low-cost judges from different providers matched the human conclusion more often than single-judge conclusions (+0.10 precision), but the gain came from filtering out one poorly aligned judge, and replication involving that judge left a conclusion for only 35% of comparisons. Judges that agreed with humans reached a stable conclusion with no more verdicts than human votes required; the others failed to converge on 26-70% of system pairs at the sample sizes tested (up to 100 verdicts per pair). Disagreements with the human vote co-occurred across judges far more often than independence predicts, although a single human vote per battle cannot separate shared judge bias from voter noise.
Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents
arXiv:2610.37679v1 Announce Type: new Abstract: Tool-using language agents are vulnerable to indirect prompt injection, and a growing literature probes model internals to catch unsafe actions before they execute, with sharply conflicting results. We argue much of the conflict is an evaluation artifact, and propose a double-stratification protocol: separate injection exposure from behavioral commitment, in both the evaluation and the training population. On the primary Qwen AgentDojo grid, monitors trained on the naive mixed unsafe-versus-rest contrast mostly learn exposure: they flag exposed trajectories whether or not the agent complies, and barely predict which cases turn unsafe. Retrained on exposed cases only, the same probe families predict the model's own unsafe tool call up to two s