Andrew Ng has announced OpenWorker, an open-source desktop agent that produces completed work slightly than dialog. OpenEmployee asks the person for an final result, not a immediate: a elegant doc, a Slack reply containing the precise numbers, an up to date calendar, a triaged inbox. It then breaks that final result into steps, works throughout…
A brand new benchmark out of the University of Michigan simply handed six frontier AI agents a causal reasoning examination. The scores expose a niche that uncooked functionality metrics are inclined to paper over. The benchmark is named CausalDS, revealed on arXiv on July 9, 2026, by Andrej Leban and Yuekai Sun. It exams one…
Tokenization is the one a part of the language modeling stack that nearly no person profiles. Gigatoken, launched by Marcel Rød (a PhD pupil from Stanford) underneath an MIT license, argues that this was a mistake. The library encodes textual content at gigabytes per second on a single machine, in opposition to baselines that are…
Anthropic has launched the Claude Security plugin for Claude Code in beta. The plugin runs a multi-agent vulnerability scan of a repository from inside an present Claude Code session, then turns the findings you choose into patch recordsdata that you simply overview and apply your self. Anthropic emphasised the software’s versatility upon announcement, highlighting its…
Cursor has made Cursor Router usually accessible for Teams and Enterprise plans. The system is a classifier that inspects every request earlier than a mannequin runs, then dispatches it to the mannequin finest suited to that particular activity. The cursor workforce reviews frontier-quality efficiency at 60% financial savings in on-line A/B exams, and 30–50% financial…
In this tutorial, we discover EdgeBench as a sensible benchmark for evaluating superior AI brokers throughout various job classes, runtime environments, and interaction-time budgets. We start by downloading the dataset snapshot from Hugging Face, parsing the launched job specs, and analyzing the benchmark taxonomy, execution settings, web necessities, judging logic, and scoring metadata. We then…
Four open supply tasks dominate LLM fine-tuning at present. Unsloth, Axolotl, TRL, and LLaMA-Factory all wrap the identical underlying PyTorch and Hugging Face stack. They diverge on the place they spend engineering effort. Unsloth rewrites kernels. Axolotl composes parallelism methods. TRL defines the coach APIs the others construct on. LLaMA-Factory optimizes for breadth of mannequin…
Poolside has launched Laguna S 2.1, a 118B-parameter open-weight mannequin constructed for agentic coding. It is a Mixture-of-Experts (MoE) mannequin with 8B activated parameters per token. It helps a context window of as much as 1M tokens in each pondering and no-thinking modes. The weights are on Hugging Face beneath an OpenMDW-1.1 license, and the…
Developers constructing manufacturing brokers want larger token effectivity, decrease latency, and extra dependable efficiency. Today, Google has released three new Gemini models. The lineup is Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, and Gemini 3.5 Flash Cyber. All three sit within the Flash tier, which Google tunes for velocity, price, and high-volume agentic work slightly than…
Meta has launched Astryx, an open supply design system that’s absolutely customizable and constructed to be operated by each folks and the AI brokers working alongside them. It is offered now in Beta. Astryx will not be a new experiment. It grew inside Meta during the last eight years, the place the corporate says it…