Full-text search across 69549 articles. Combine with topic and date filters; results sorted by relevance.
Barracuda research published on October 7, 2026 describes phishing emails built to target both human recipients and AI assistants, pairing a password-protected attachment for the person with hidden prompt-injection instr…
A developer built deploy.me, an MIT-licensed, self-hosted deployment tool that runs locally in Docker and pushes projects to servers using only ssh, rsync and docker compose. The app offers a tmux-style interface, atomic…
Cognition, the startup behind the autonomous coding agent Devin, built an internal system that grades engineers on AI efficiency — human-equivalent engineering hours produced per dollar of token spend — and raises spendi…
A developer published a TypeScript approval-gate pattern that assigns autonomy levels 0 through 4 to individual tools rather than whole agents, classifying each tool as read, write or irreversible and routing calls to al…
A developer built Package Safety Checker, a RapidAPI-hosted endpoint that queries npm, PyPI, crates.io, Go, Maven and NuGet registries to verify whether a package exists before an AI agent installs it, returning a verdic…
A developer drafted a technical article for Dev.to and Paragraph.com explaining the x402 protocol, Coinbase's open standard that revives the HTTP 402 "Payment Required" status code for machine-to-machine payments over HT…
Developer rvdende released cadrs, an open-source parametric CAD application written in Rust with a Bevy UI and the OpenCASCADE modeling kernel, following Onshape's sketch-part-assembly-drawing workflow. The project is de…
A critical vulnerability in Langflow, tracked as CVE-2026-105740 with a CVSS score of 9.9, allows authenticated low-privileged users to achieve remote code execution by saving MCP Stdio commands that Langflow passes unva…
Kong shipped Volcano, a full-stack agent infrastructure platform bundling eight generally available services — including durable compute with 366-day execution windows, branchable PostgreSQL with pgvector, edge functions…
A developer demonstrated that the open-source NeuralCodec-8K model, which replaces traditional motion estimation, DCT quantization and CABAC entropy coding with learned transformer and diffusion-based networks, cut a 120…
Michael Denyer released pstack-claude v0.9.86 on October 15th, 2026, a port of Cursor's pstack workflows to seven coding-agent runtimes, according to GitHub's release listing, which records the release at 21:47, commit 1…
A developer's Illumia Archive Intelligence case study documents a local Python and PostgreSQL retrieval tool, exposed through a browser interface and a Claude Desktop MCP connection, that keeps parent cases linked to the…
Cloudflare's published API specification now omits the `amount` field from `POST /accounts/{account_id}/ai-gateway/billing/topup/config`, so requests that still send it succeed but the value is silently ignored rather th…
Anthropic says its Claude model reverse-engineered the unexplained NSA seeds behind NIST's P-192, P-224, P-256, P-384 and P-521 elliptic curves in under half an hour, finding they were outputs of the 1990s C library rand…
A developer built Munim, a local-first bill diary for small Indian shop owners that uses Google's open-weight Gemma 3 vision model served via Ollama to read photographed supplier bills, then validates GST and arithmetic …
A developer's hybrid retrieval index for the Featpilot multi-repo ticket generator silently lost roughly half its keyword-indexed repos after a re-index job hit a table lock and exited with a zero status code, going unde…
An attacker spent three weeks inside a researcher's internet-facing EC2 instance and burned roughly $600,000 in METR inference credits without touching sensitive data, exploiting a vibe-coded agent app whose Google authe…
A developer built Open List, an open-source AI ecommerce listing generator that turns basic product notes into complete Etsy, eBay, Instagram, or WhatsApp listings in about three seconds. The app runs Gemma 3 1B locally …
Palo Alto startup Elorian released its first AI model, Glimpse, on Friday as a research preview with API access, priced at $0.60 per million input tokens and $3 per million output tokens. Glimpse uses a "visual scratch s…
Lemma Park launched as an autonomous community research lab that lets participants lend their coding agents' spare compute to open mathematical problems, in the spirit of Folding@home. The lab reports 69 verified results…