arXiv:2609.09233v1 Announce Type: new Abstract: How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containing instructions, scripts, and other resources that help agents perform specific tasks. Agent skills are typically executed by loading their skill instructions into an agent's context and relying on the agent to follow them. As task horizons grow, however, this approach becomes increasingly brittle, because reasoning quality degrades as more information accumulates in the context window. We investigate an alternative approach in which skill packages are instead invoked as subagents. Rather than…

arXiv:2609.09226v1 Announce Type: new Abstract: We introduce a probability-wave framework for modeling the collective behavior of interacting adaptive agents, deriving testable eigenmodes through a generalized behavioral intelligence (GBI) nonlocal probability-wave equation. This framework captures a broad range of human intelligence behaviors with analytical mechanisms and offers an indirect method to examine the Liu-Chen-Ao (LCA) hypothesis of nonlocal entangled nerve fibers in the brain through collective trader behaviors. Our empirical analysis of Chinese intraday stock market data demonstrates that adaptive entangled game modes explain 82-94% (89% overall) of observed decision patterns, a sharp contrast to the predictions of neoclassical finance based on independent rational agents.…

arXiv:2609.09203v1 Announce Type: new Abstract: Existing benchmarks for autonomous AI scientists evaluate only final outputs---generated code, hypotheses, or papers---yet discard the reasoning process by which those outputs were obtained. This makes it impossible to audit scientific methodology, diagnose failure modes, or distinguish systematic reasoning from fortunate guessing. We present \textbf{OpenDiscoveryTrace}, a public dataset of 558 complete AI scientific agent trajectories that captures how models reason, not just what they produce. Each trajectory records a structured 9-field-per-step trace---including thoughts, tool calls, observations, errors, revision triggers, and self-reported confidence---as models execute 124 scientific tasks spanning drug discovery, materials science, g…

Datasette 1.0a39 and 0.65.4 security releases Today we're releasing two new security patch versions of Datasette: 1.0a39 and 0.65.4 - one for the current alpha series and one for the stable 0.65.x family. These are security fixes which you should apply if you are running a Datasette instance on the public web - in particular if that instance mixes both public and private tables. Following issues reported by Sevban Dönmez, Alex Garcia and I ran an extensive audit of Datasette using Claude Fable 5.1, GPT-5.6, and GPT-6 Astra. We then spent almost a week collaborating on and reviewing the fixes. They helped find some very subtle bugs. We'll be incorporating security audits by frontier models into all of our development work going forward. Alex came up with a way of splitting the work which I…

Release: datasette-publish-fly 1.4 Sets force_https=true in fly.toml. #31 Fix for Volume could not be found bug. #32 Compatible with app-scoped deploy tokens. #34 Tags: datasette, fly

It’s a better interface, can speed installations, and drives IaaS sales too

Release: github-to-sqlite 2.9.1 Fix for compatibility with sqlite-utils 4.x. #85 Tags: github, sqlite

Discussion | Link

Discussion | Link

Release: datasette 0.65.4 See Datasette 1.0a39 and 0.65.4 security releases on the Datasette blog. Tags: security, datasette

Together Fine-Tuning adds the latest open-weight models, live experiment tracking, Expert LoRA, early stopping, tokenized dataset previews, pre-flight validation, and lower training prices on selected models.

Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e…

Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the “one-to-many” nature of video description, where high-quality captions are often penalized for lexical mismatches or valid shifts in visual focus. Furthermore, such assessments are typically one-dimensional, failing to provide a fine-grained analysis of caption quality. To address this, we redefine caption quality via information fidelity: A caption must maximize the coverage…

Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic research. We address three key phenomena within our modular Large Language Model (LLM)-based translation framework: (i) spatial coreference resolution, where entities maintain consistent spatial locations throughout discourse; (ii) Question-Answer Clauses (QACs), pseudocleft structures serving…

Any Nix package, live in your browser Farid Zakaria calls this his "magnum opus of Nix work", and I can see why. trynix.dev provides a qemu-wasm powered x86_64 Linux virtual machine running entirely in your browser through WebAssembly. That VM can then be booted with any Nix package from the past 13 years. They are URL addressable, so you can navigate to this page: https://trynix.dev/?pkg=python3%403.6.2 Then click "Load" and get an interactive shell against a virtual machine running Python 3.6.2 from 2017. Farid is building all sorts of neat things on top of this. One recent example: Review a pull request by booting it introduces trynix-preview, described like this: GitHub action that comments a link on a pull request which lets you boot the PR’s build in the browser using https://trynix…

Discussion | Link

Amazon Web Services (AWS) has released a new open-source application dubbed Pizza Bot, which gives developers an email-style inbox for The post AWS open-sources Pizza Bot: email-style inbox for background AI agents appeared first on The New Stack.

Machine Intelligence

Discussion | Link

Discussion | Link

Mathematics relies on a community of experts openly sharing ideas.

The competitive landscape, particularly the geopolitical clash between the U.S. and China, complicates the AI safety dilemma.

Report comes two days after former employee quit claiming company’s models could cause human extinction by 2030 Criminals, state-sponsored groups, spyware vendors, scientists and propagandists have attempted to use Anthropic’s powerful artificial intelligence models to design missiles and bombs, create deadly pathogens and surveil dissidents, according to a threat intelligence report the company published on Thursday. “The cases we share here aren’t typical misuse, but rather examples of the most notable and novel threat activity we’ve identified to date,” Anthropic wrote in its 154-page report. “We’re publishing this work because we believe we have a responsibility to disclose malicious misuse of our services.” Continue reading...

Production LLM applications rarely receive a question nobody has asked before. Support assistants and RAG pipelines field the same intents thousands of times a day, each phrased differently, and most stacks treat every phrasing as a fresh, fully billed request. Redis LangCache is a fully managed semantic caching service that sits between the application and […] The post Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster appeared first on MarkTechPost.

Discussion | Link

Discussion | Link

Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llama 3.1 70B, it reduced P50 time-to-first-token by up to 77% and raised KV cache hit rates from about 25% to over 80%.

NVIDIA has detailed BioNeMo Inference Runtime (BioIR), a Python library that accelerates biomolecular structure-prediction models on NVIDIA GPUs while staying in plain PyTorch. In a matched benchmark on 1,000 human dimer targets across 8xH100 GPUs, BioIR-accelerated Boltz-2 delivered 58.5K successfully folded residues per GPU-hour versus 20.2K for a torch-compiled open-source implementation, a 2.90x gain. The runtime optimizes at 3 layers: custom kernel selection, CUDA Graph capture, and Ray-based replica scaling that places 1 full model copy per GPU. BioIR already powered the AlphaFold Database expansion, generating about 31 million candidate protein complexes across 4,777 proteomes. The post NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58…

Insiders at the firm fear tech’s advancement could cause human extinction while others are calling it a ‘setup’ A day after a former researcher at Anthropic made an apocalyptic declaration about artificial intelligence, more researchers and staff members at the AI startup publicly agreed with him and posted their own dire warnings. In response, Elon Musk and other conservative figures on X, formerly Twitter, called the chorus of concerns a “setup” and a “psyop”. Continue reading...

Amazon SageMaker HyperPod now supports model caching for inference, which pre-loads model weights and container images onto cluster nodes so pods read from local NVMe storage instead of downloading over the network. Learn how model caching cuts cold starts from tens of minutes to seconds, how it works, and how to enable it.