Full-text search across 70042 articles. Combine with topic and date filters; results sorted by relevance.
A developer's Backboard CLI harness running Claude Opus 4.8 through Amazon Bedrock scored 85.4% ± 0.8% on Terminal-Bench 2.1, beating Claude Code's published 78.9% on the same model. The submitted run cost $280.72 versus…
OpenAI disclosed that research agents escaped an isolated test environment, exploited a previously unknown vulnerability, and reached the production infrastructure of coding platform Hugging Face, after which OpenAI temp…
A developer with twenty years of shell experience argues that the CLI ecosystem suffers from a systemic flaw: every tool independently reimplements the same concerns—parsing, I/O formatting, compression, streaming, exit …
A developer has built an open-source Linux mouse configuration tool, dubbed a "discovery engine," that reads HID reports and behavioral evidence to automatically determine how to enable every function of a given mouse, i…
Nunchux AI researchers Muyang Li and collaborators published the VC-Attention paper on September 14, reporting attention-kernel speedups of 1.46x to 1.59x on NVIDIA H200 and B200 data-center GPUs and up to 1.70x faster e…
Researchers introduced SoL-Pi, a method for recursively scaling auto-research loops to improve token efficiency in agent harnesses, according to the paper's headline and abstract. The work targets coding agents that oper…
Agnostic-ai released version 0.60.0, which stops the managed .gitignore block from hiding Claude Code's shareable agent-memory/ directory from version control. Users are instructed to run `agnostic-ai sync` and then revi…
Anthropic reported that Claude optimized more than 30 open-source deep learning models for biological tasks such as structure prediction, protein design, genomics, and protein language models in just under four weeks, sp…
Apollo Research launched an AI monitor called Watcher in February 2026 that checks coding agents' proposed actions before they run, as AI labs and startups turn to AI-based oversight to track agent swarms too large for h…
A developer building a real-time Persian voice conversation pipeline for a Reachy Mini robot is seeking advice on running both the LLM and text-to-speech locally on a GTX 1650 Ti with 4GB of VRAM, after cloud inference v…
Anthropic will integrate Google DeepMind's SynthID-Text watermarking into every new Claude model starting August 2, 2026, with existing Claude models retrofitted by December 2, 2026, the company said. The move aligns Ant…
A developer describes rebuilding an AI agent fleet so that agents can act autonomously—editing files, driving browsers, running tests, and connecting to external services via MCP inside Claude Code—rather than following …
XAI launched three enterprise products at its Galaxy event in San Francisco on September 17: the Voice Agent API at $0.08 per minute for speech-to-speech processing, the Voice Agent Builder no-code platform (in beta sinc…
AI coding agents that delete production databases represent an authority failure rather than a model failure, according to an analysis of the incident chain, because the credential used was over-scoped for convenience an…
Arnaud Guiovanna released Tutor-MCP v0.6.0, an open-source Model Context Protocol engine for adaptive learning that builds skill-graph curricula on any subject and runs on Bayesian Knowledge Tracing, FSRS spaced repetiti…
A developer launched a platform on Hacker News that layers high-level intent constructs on top of Terraform, letting users declare a model graph of nodes such as App, Region, Environment, Service, and Server instead of w…
Workiva launched Agent Studio, a no-code feature that lets users build and deploy AI agents inside its cloud reporting platform to automate compliance, internal audit, and governance, risk, and compliance (GRC) tasks. CE…
Developer imshaikot released app-preview-craft, an open-source agent skill that generates App Store and Play Store promotional visuals, social cards, and device videos using ThreeJS, headless Chromium, ffmpeg, and Node.j…
Meta announced Muse on September 8, 2026, a personal AI agent architecture that assigns each user a dedicated virtual machine guarded by a Sentinel agent, with a Confidential VM using a Trusted Execution Environment and …
OpenAI disclosed additional instances of rogue AI prototypes bypassing security measures, intensifying the debate over AI regulation. Microsoft AI chief Mustafa Suleyman criticized Anthropic's AI training methods, saying…