Full-text search across 71253 articles. Combine with topic and date filters; results sorted by relevance.
A developer has published a practical guide to writing agent instruction files that measurably change behavior, centered on a five-line rule in a global CLAUDE.md that assigns subagent models by task difficulty (haiku fo…
Uber built an internal MCP Gateway that now hosts over 800 MCP servers and more than 5,000 tools, centralizing how AI agents reach the company's back-end services, Uber engineers reported. The platform pairs an MCP Regis…
MariaDB on Wednesday added four agent-focused capabilities to Enterprise Platform 2027: AI Retrieval, AI Plugins, Agent Memory and Semantic Cache. AI Retrieval converts natural-language questions into read-only SQL queri…
Anthropic's Claude API prompt caching lets developers reuse an unchanged prompt prefix at a cache-read rate generally reported at 0.1x of the base input price, with a 5-minute cache write at 1.25x and a 1-hour write at 2…
Colloq, an open-source self-hosted classroom tool from the colloq-edu project, lets a teacher share one link so students join a single live Python notebook from a browser with only a name, with no accounts or installs. T…
A scan by German security research group Crissy Field, conducted with business daily Handelsblatt and first reported November 2, found that 24,664 of 34,545 Lovable-built projects running on Supabase returned database re…
Wiz is marketing its Green Agent as a way to cut remediation bottlenecks by automatically identifying a "Suggested Assignee" for each security Issue, drawing on repository commit history, Wiz Project assignments, service…
Agents using GitHits read every dependency at the lockfile-pinned version in all 192 runs, compared with 94.8% of runs for agents that cloned dependencies themselves and 66.1% for agents starting from a prebuilt snapshot…
An open-source Model Context Protocol server called maat lets AI agents diagnose Ubuntu systems from inside a strictly confined snap with read-only permissions and no network access, while any fix must be approved by a h…
Meta released the weights of Muse Spark Open in October 2026, an 816B-parameter mixture-of-experts model that activates 42B parameters per token and supports a 1M-token context window, scoring 89.2 on the MCP-Atlas tool-…
Anthropic added message threads to its Messages API as a public beta on November 2, 2026, behind the `message-threads-2026-08-12` header, letting agent loops send only new messages per turn instead of re-uploading the fu…
A practitioner who spent eighteen months deploying long-running AI agents argues that most 2026 agent patterns are older distributed systems and compiler ideas — MapReduce, write-ahead logs, two-phase commits, actor mail…
Hugging Face released FineDNA, the full training dataset behind Carbon-X, the model that adapted Qwen3-14B to read DNA across all three of its training stages. The mid-training stage comprises 23 configs totaling 514.30B…
A Hugging Face repository named burner22/numbat claiming to hold a leaked 14T-parameter checkpoint of Anthropic's next Mythos-class model is almost certainly fake, according to a public audit posted in the repo's discuss…
ContextuAI released Hey Spark, an open-source always-listening voice assistant for macOS 14+ on Apple Silicon and Windows 11 that runs wake-word detection (openWakeWord), speech-to-text (faster-whisper) and text-to-speec…
Arca, an AI-native wealth-management company, runs agents on client work that can span up to ten days while keeping human advisors in charge of every decision touching client money, lead AI engineer Aman Singh said in a …
Anthropic is embedding an invisible statistical watermark into text generated by its supported Claude models to comply with Article 50 of the EU AI Act, which requires machine-readable marking of synthetic content starti…
Z.ai's open-weight GLM 5.3 model, released in August, autonomously built a working Firefox exploit that read files from a visitor's computer and exfiltrated them with no user interaction, compromising any Firefox version…
The Central Institute of Indian Languages (CIIL) launched Anuvani, an open-source speech-AI ecosystem, with its first two public open-weight models, Anuvani-LID and Anuvani-Diarization, covering all 22 scheduled Indian l…
A test run on 26 October 2026 of 49 runs by 23 AI agents, chatbots and developer tools against a purpose-built three-page site found that most browser-using agents look exactly like a person in Chrome, reporting no autom…