Full-text search across 69564 articles. Combine with topic and date filters; results sorted by relevance.
A critical authentication bypass in the PraisonAI multi-agent orchestration framework, tracked as CVE-2026-44338 with a CVSS score of 7.3, was probed by an automated scanner 3 hours, 44 minutes, and 39 seconds after a Gi…
Meta expanded its Muse AI agent into personal finance, adding skills that connect to bank portals to detect recurring subscription charges, compare insurance policies, and negotiate household service contracts on users' …
A developer built MDPreview, a zero-latency, fully client-side Markdown viewer and live editor that parses and highlights documents entirely in the browser without uploading any text to a backend. The tool, built with Vi…
A data engineer built a multi-agent AI debugging system on LangGraph that automates data metric root-cause investigations, cutting tasks that previously consumed 30% to 50% of engineers' time down to minutes. The system …
InclusionAI's Ling 3.1 Flash, a hybrid reasoning language model with 560B total parameters and 25B active per token, is now available on Vercel's AI Gateway and free to use through October 13, 2026. The model offers a 26…
PTXBench, a benchmark released August 17, 2026 with code on GitHub, evaluates how well frontier LLMs can write architecture-specific CUDA-PTX for H100 and B200 GPUs, finding GEMM nearly solved while attention lags. Claud…
A developer's analysis of MCP issue trackers across Copilot CLI, Gemini CLI, Cursor, Open WebUI, Codex and homegrown gateways finds that most "token expired" failures stem from conflating two independent clocks: OAuth ac…
OpenAI shipped more than 20 products at DevDay 2026 on 29 September in San Francisco, headlined by dots, an always-on agent running on GPT-6 Astra that persists context across ChatGPT, Slack and 4,000+ plugin application…
OpenAI's GPT-6.1 Sol is now generally available on Amazon Bedrock, delivering what OpenAI calls near-Astra intelligence for agentic coding, computer use, and professional workloads. According to OpenAI, GPT-6.1 Sol match…
OpenAI announced at its annual DevDay that ChatGPT Pro subscribers paying $200 per month will see their usage allowance cut in half, from 20 times the $20-per-month Plus plan to 10 times, alongside a new $500-per-month P…
OpenAI released GPT-6.1 Sol, a model the company says delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work, priced at $2.00 per 1M input tokens and $10.00 per 1M output …
Postman launched the Postman plugin for OpenAI Codex, bringing Postman's agent skills into Codex sessions so the coding agent runs the Postman CLI instead of guessing at curl commands. The plugin installs either via the …
Google announced general availability of GKE Agent Sandbox optimized for reinforcement learning, along with an Agent Sandbox RL orchestration SDK and native integrations for RL gyms and harnesses, claiming 45x faster san…
Goose, a general-purpose AI agent built in Rust and governed by the Agentic AI Foundation at the Linux Foundation, has drawn 45,000+ GitHub stars and 500+ contributors, according to the project's repository listing. Goos…
Oya launched a source-available browser automation product that records an agent-driven browser task once and replays it afterward with no LLM in the loop, running a real headful Chrome rather than headless Chrome over t…
A developer built a deal intelligence agent that uses Hindsight AI's episodic memory core to retain objections, competitor mentions, stakeholder concerns and pricing discussions across multi-month sales cycles, replacing…
SebaSOFT released neuron-js, an MIT-licensed TypeScript library that stores business rules as pure JSON ExecutionScripts, validates them before execution, and produces an ExecutionExplanation trace of which rules and con…
A developer released pi-grok-agent, an npm package that runs xAI's Grok Build agent as a model provider inside the Pi coding agent, installable via `pi install npm:pi-grok-agent`. The package connects Grok Build over the…
Anthropic published a prompting guide for Claude Opus 5.5, which launched Sept. 22, advising developers to test multiple effort levels rather than reuse Claude Opus 5 settings and to remove system-prompt lines telling th…
Anthropic released Claude Sonnet 5.5 on Monday, a lower-cost complement to its Opus 5.5 model that runs 30% faster than Claude Sonnet 5 and costs up to 30% less for most tasks by using fewer tokens, the company said. Son…