Full-text search across 17588 articles. Combine with topic and date filters; results sorted by relevance.
A developer in Indore, India built Dharohar, an open-source, audio-first heritage walking guide that uses a Mastra agent with SerpApi and Google's Gemma models to generate spoken scripts for nearby monuments and then del…
OpenAI released Auto-review in Codex, a mode that replaces human approval at the sandbox boundary with review by a separate Codex agent, cutting how often Codex sessions stop for human approval by roughly 200x compared w…
A developer launched acceptodds, a prediction market where users bet on whether each of the 42,000 ICLR 2027 submissions will be accepted or rejected, using Hanson's logarithmic market scoring rule (LMSR) to set prices. …
A nine-month review of security incidents from December 2025 through September 2026 documents how credential theft evolved into autonomous AI-driven credential misuse, citing 28.6 million secrets exposed on public GitHub…
A former Developer Relations lead for a privacy-focused smart contract platform tested whether AI coding agents could write correct contracts in the platform's TypeScript-like language, finding that three of four attempt…
Esgenix, an agentic AI patent workflow platform led by CEO and co-founder C R Jacob, launched Self-Serve on October 2, 2026, giving solo practitioners, independent inventors, startups and small IP firms pay-as-you-go acc…
Anthropic's Claude flagged a Florida woman's diary-style entry about wanting to "shoot up" a sheriff's office, and a human reviewer escalated it to police, leaving her facing a second-degree felony, TechSpot reported. Se…
Researchers introduced KCoral, a lightweight benchmark server that decouples GPU execution from AI agent loops so many agents can share a small pool of GPUs. KCoral uses an atomic HTTP protocol with four operations — upl…
A developer has released T-Zero Context Architect V3, an open-source tool that uses AST-based static analysis to strip function implementations from a codebase while preserving signatures, docstrings, decorators and impo…
Alibaba's DAMO Academy, with Renmin University of China and the University of Chinese Academy of Sciences, unveiled Elements Claw on July 3, 2026, an AI agent that screened 2.4 million candidate crystal structures in 28 …
A developer built Hacktoberfest Starter, an open-source Streamlit app that matches developers to GitHub issues based on their skills and proficiency levels, filtering out issues that appear already claimed or unsuitable.…
Princeton researchers Adithya Bhaskar, Jeffrey Cheng and Danqi Chen built Queen, a 4-billion-parameter language model that climbed from 1782 Elo to 2697 Elo over seven rounds of training, a gain of more than 900 points, …
At Rocky Mountain Ruby in Boulder, Colorado, speakers including Drew Bragg, Giovanni Panasiti, Andrea Fomera, and Ifat Ribon presented practical approaches to building AI agents and agentic RAG in Ruby, with Bragg live-c…
A technical explainer on knowledge cutoffs and parametric memory states that Allen-Zhu and Li (2024) measured a language model's knowledge capacity at about 2 bits per parameter when each fact appears roughly 1,000 times…
Utah granted Nolla Health approval to launch a pilot letting an AI system issue acne prescriptions without prior physician sign-off, making it the first U.S. state to permit automated prescribing, according to the compan…
Anthropic announced its Model Hardware Standard (MHS) at the end of August as an open interface for connecting AI models and agents to hardware, and received 30x more organizations requesting to participate in the first …
Reflection AI Inc. introduced Beam, an open-source large language model with 501 billion parameters, which the company says matches or beats GLM-5.2 on some tasks while using between one third and one fourth the hardware…
The Wikimedia Foundation disclosed on October 5 that an internal investigation tied "rogue" OpenAI agent activity to a partial outage of its Wikidata Query Service that ran from May 7 to May 11, with more than half of re…
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…
Niantic Spatial CEO Inhi Cho Suh said organizations cannot delegate decades of risk, compliance and measurement work to a single model, speaking on the Zero-Shot Learning podcast alongside Director of Product Management …