Search headlines, summaries and articles to connect the dots.
Learn how to build a serverless Model Context Protocol (MCP) server on Amazon ECS with AWS Fargate that gives AI agents secure, metadata-driven access to an enterprise data lake. Exposing a new dataset requires only a JSON file, with no per-dataset integration code.
Article URL: https://github.com/Kirby54/Select Comments URL: https://news.ycombinator.com/item?id=50400882 Points: 1 # Comments: 0
Article URL: https://hodor.gatebolt.com/blog/secret-leak-test Comments URL: https://news.ycombinator.com/item?id=50401639 Points: 1 # Comments: 0
Anthropic is using AI to build more powerful AI. And it appears to be working remarkably well, with the company's models improving roughly twice as quickly as a year ago, with little indication of slowing down. That's according to a new report published Thursday by the AI safety research organization METR, following an 11-week investigation […]
arXiv:2611.07132v1 Announce Type: new Abstract: We present an automated method for auditing text-to-image generators for representational bias against ground-truth demographic benchmarks. Our approach adapts the racial proxy variables used in U.S. antidiscrimination law to provide a fine-grained comparative analysis of variations in racial representation in generated images. We classify each generated image by race and then compare the model's distribution to publicly available demographic benchmark data to identify patterns of over- and under-representation. We also measure skin tone using CIELAB values and calculate cosine similarity amongst groups of images in order to capture biases that don't show up in demographic comparisons such as differences in image quality across races and skin tones. We report on experiments testing three models (Imagen 4 Fast, Stable Diffusion 3.5 Large Turbo, and Flux Schnell) using three categories of proxies (geographic, occupational, and surname) and 50 variants within each category. We find notable variation across the models as well as by proxy category. For example, Imagen 4 Fast overrepresents white classified images more than the other models tested and produces images with lighter, more homogeneous skin tones. Imagen 4 Fast also had the largest representational disparity for Black demographics among surname and geographical prompts. Stable Diffusion 3.5 Large Turbo produces results that overall diverge most from census data but yield the most diverse range of skin tones. Our method yields a generalizable and legally-grounded auditing tool that surfaces detailed information about model outputs without relying on implicit normative definitions of fairness.
Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.
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.
Learn how Amazon Marketplace evaluates A+ Content quality at scale on Amazon SageMaker AI by rendering each product page as a single snapshot, scoring it with a vision-language model fused with OCR readability signals in a CatBoost classifier, and using SHAP to turn each decision into prioritized, actionable recommendations for selling partners.
OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.
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.
arXiv:2611.06065v1 Announce Type: new Abstract: In natural human-AI dialogue, users' corrections, requests, and self-descriptions carry reusable signals about how they want work to be done. These signals reveal individual process preferences, user-specific standards for evidence, depth, analytical focus, procedure, and delivery. We ask whether a preference revealed in one dialogue can shape an assistant's later answer when the task does not restate it. ProcessPrefBench uses three months of natural dialogues from two knowledge workers to build 66 source-target cases separately judged for source evidence and target applicability. Sources are preselected, so the benchmark tests application rather than retrieval. We test three models with target-only, full-history, and distilled-preference prompts. Target-specific 0-2 rubrics score preference realization, and a task gate flags severe failures. Compared with target-only prompting, full-history and imperative distilled-preference prompting raise preference realization by 0.204 and 0.244 points on the 0-2 scale, respectively, with no reliable advantage from distillation. Fabricated-evidence failures rise from 5.8% under target-only prompting to 10.1% under full-history and 10.4% under imperative prompting. ProcessPrefBench highlights a tension in learning from dialogue, where drawing on prior interactions can improve preference realization yet also invite fabricated evidence. We hope it helps build assistants that honor a user's process preferences without sacrificing factual reliability.
Here is Cerea, a self-hostable, open-source (Apache 2.0) chat+agent frontend for LLMs. It works alone with any OpenAI-compatible inference provider, but it's way better when coupled with the model gateway I'm also developing, Pystino (https://github.com/paoloviviani/Pystino).I came to this after struggling to find a hosted chat interface that was truly open source, that I really enjoyed to use, and that was simple enough to be shared and used by family. In particular, I was looking for something that could provide the smooth and integrated user experience of commercial products for the tasks needed by family (e.g., document editing, form filling, notes and knowledge management), but backed by open models hosted wherever I decide.Then it became richer, now supporting: remote coding agents (wrapping Opencode), delegation and coordination between agents, integration between chat/projects and code agents (this one to me is a pain point for Claude, which I use at work), projects, RAG, rich artifacts support, schedules, and more.You can try it yourself, either cloning the full repo and head to Cerea/kit, or just the deploy kit with a script (https://github.com/paoloviviani/Cerea#quick-start).It's just a docker compose with a ./configure script that helps to generate a sensible .env for the specific scenario. It works in the browser and as a PWA on mobile.I hope you'll enjoy, feel free to reach out for questions. Comments URL: https://news.ycombinator.com/item?id=50384502 Points: 1 # Comments: 0
I built it to replace the repetitive workflows of moving tabs and copying indicators across many tools and tabs for every investigation. You use your own API keys, and functions like decoding, identifying commands, and man pages all run locally with no LLM.Please let me know what you think, you can try it here right now. More information about it can be found here: ceplang.org/start.htmlAs well as a short demo here: https://youtu.be/bzGGigpeiXg Comments URL: https://news.ycombinator.com/item?id=50391790 Points: 1 # Comments: 0
Article URL: https://github.com/llmbrake/llmbrake Comments URL: https://news.ycombinator.com/item?id=50386174 Points: 2 # Comments: 0
Hi HN,I've been fascinated by aviation for some time now. Inspired by Fugleramme, I wanted a framed print of a cluster of aircraft over my house or a busy airport. So I built Overhead. (Photos in the README)The hero photo shows planes departing and landing in Changi, Singapore.How it worksFlight data for a location is gathered from adsb.lol and adsb.fi as a fallback. (you can also point it to your own ADS-B receiver).The photo of the exact aircraft is gathered from planespotters.net and the photographer is credited on the page.The photo is then handed to an AI image gen service via fal.ai using your own key.It's then cut out and packed into a cluster on the page with packers adapted from Fugleramme.It costs about US$0.04 a painting but images are painted once and kept for the next time that aircraft is seen.You can also choose to only show photos.This widget is built on my open source, self-hosted e-ink platform, Tesserae. It's a one click install from the widget catalog.I'm looking for feedback and contributors.https://github.com/arnegiacomo/fugleramme https://github.com/dmellok/tesserae Comments URL: https://news.ycombinator.com/item?id=50390605 Points: 1 # Comments: 0
Article URL: https://github.com/SimakovIgor/pixel-buddy Comments URL: https://news.ycombinator.com/item?id=50389351 Points: 2 # Comments: 0
Been using this in all my sessions the last months. Opus 5.5 (over MCP) spawns Deepseek flash agents - and codex for audits etc. Very curious to hear what the HN crowd thinks/makes of it. Comments URL: https://news.ycombinator.com/item?id=50383189 Points: 1 # Comments: 0
arXiv:2611.06025v1 Announce Type: new Abstract: When a language model chooses a number between 1 and 30, every integer in the range is valid, yet the model can favor particular answers. We use numerical choice to study how preference is processed across layers and tokens. Perturbation probing and gradient attribution nominate neurons for activation interventions. In a selected Qwen3-4B case, a pre-answer edit changes 17 to 15 while both runs first emit 1. After the edit ends, selective cache and attention-output replacements trace part of its continuing influence on the second digit. Replacing one attention head's output or the other heads' outputs jointly produces similar immediate readout contributions; both interventions restore 17 but have different final log-odds effects on 7 versus 5. Holding later multilayer perceptron (MLP) outputs at their values from the edited run without either replacement reduces this effect gap from 0.119 to 0.0025 nat. Later computation therefore changes how similar local contributions affect the continuation. Retrospective estimates across eighteen contexts capture much of the probability movement but miss the selected answer switch. Prompt tests also separate influence from answer changes: one held-out prompt retains influence without switching, and only one of twelve fresh wordings qualifies for the reader/MLP test; there, joint MLP clamping again reduces the gap between the two reader effects while the answer remains 17. These results use numerical choice as a controlled case for studying persistent state and conditional downstream processing; they do not establish the origin or a complete circuit of natural numerical preference.
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.
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.
