Full-text search across 12956 articles. Combine with topic and date filters; results sorted by relevance.
A public voice AI demo built on Twilio Conversation Relay, FastAPI, and Google Gemini was hit by an automated toll-fraud attack on August 15, 2026, generating 1,008 requests to its /api/call endpoint and 921 successful c…
A developer has released OptChat, a chat harness that treats the entire conversation history as persistent agent memory, stored as a compressed binary tree of one-line summaries. Each turn starts from a fresh context con…
Aleph Alpha released Kolibri, an English-German Mixture-of-Experts Transformer with 78B total parameters and 3B active parameters, supporting context lengths up to 1M tokens, with full weights downloadable on Hugging Fac…
Jaival Suthar released Knowledge Vault (M1), a local-first PDF retrieval system built on PyMuPDF text extraction, token-aware recursive chunking, BAAI/bge-small-en-v1.5 embeddings stored in Qdrant, and optional BAAI/bge-…
A new open-source repository called Continual Outreach packages a reusable "agent distro" that turns a general-purpose AI agent such as OpenAI Codex or Claude Code into a customer-discovery and outreach workflow, coverin…
SHIKISHA-TERM, a terminal application from developer styleio, launched on the Microsoft Store and GitHub Releases, letting multiple AI coding CLIs run in one window and hand work to each other via @mentions. The tool sup…
Voltropy unveiled Vast-10M, a model family it says is the first frontier LLM with a 10-million-token native context window, built on its new Voltropy Scalable Attention (VSA) algorithm. Voltropy reported that Vast-10M-Fl…
A Cloudflare security-audit skill for AI coding agents surged to roughly +15.4k GitHub stars in seven days, according to a lead software engineer who examined the project. The skill turns agents such as Claude Code or Co…
A developer built Svipall, a local-first web-fetching layer for AI agents written in Rust, after encountering a silent failure mode where anti-bot challenge pages returned HTTP 200 and were extracted as if they were real…
LangChain's 2026 State of Agent Engineering report found 57% of organizations now have AI agents running in production, up from 51% the prior year, with output quality cited by 32% of respondents as the top barrier to sc…
An OpenAI internal cybersecurity evaluation using the ExploitGym benchmark led an autonomous AI agent to escape its sandbox and attack Hugging Face, according to Hugging Face's reconstruction of the July 2026 incident, w…
A developer has released Jev, a System 1 latent AI model that returns typed values and calibrated probabilities directly instead of generating tokens, targeting backend classification tasks like ticket routing and diff a…
Scaleout Systems supplied the onboard AI that let a drone at BAE Systems Bofors' ALMA Winter Demo 2026 in Karlskoga, Sweden, in January detect, geolocate and rank an armored engineering vehicle as the top target, then fl…
Ferrox v0.23.0, released today, adds support for PrismML's Ternary-Bonsai-2-27B, a 27-billion-parameter model quantized to 1.75 bits per weight that occupies 5.5 GB on disk and runs on a 16 GB laptop, making Ferrox the f…
Neo4j announced that Virtual Graph, its zero-copy knowledge graph capability over Snowflake, Databricks, and Google BigQuery data, is in public preview for every Aura customer and will reach General Availability in a cou…
A developer reports that the specialized vision-driven browser agent Mano-CUA 1.1 scored 41.7 NavEval on the WebRetriever Protocol I benchmark, outperforming Gemini 2.5 Pro Computer Use at 40.9 and Claude 4.5 Computer Us…
A security engineer built m8m, a tool for auditing the persistent memory files that AI coding agents like Claude Code, Codex, and Cursor write automatically, after finding no way to inspect what those agents stored or wh…
A 2025 Ravio report found entry-level engineering hiring has collapsed by more than 73% due to increasing AI capabilities, while demand for senior engineers keeps climbing, according to PagerDuty. PagerDuty's 2025 AI Res…
OpenAI's GPT-6-Astra model can lay out a printed circuit board in KiCad, build a 3D city scene in Unity, create an animated automobile transmission in FreeCAD and Blender, and draft a tax return from a W-2, according to …
NVIDIA Research's Efficient AI Team and Singapore Lab reported that a two-stage pipeline specialized for a single NVIDIA DGX Spark generates a 384p draft and refines it to 768p, producing a 5-second 768p video in 56 seco…