A security researcher known as BobDaHacker found that tl;dv, an AI meeting notetaker, left its Firestore 'meetings' collection readable by any authenticated user, exposing 181,874 meeting records from…
Docker Inc. launched Docker Sandboxes, a new product that isolates AI coding agents in microVMs with their own kernels and private Docker daemons, rather than containers, to make bypass-mode agents sa…
Meta's Superintelligence Labs released Muse Glimmer, a 30-billion-parameter dense multimodal model with 131K context, under the Apache 2.0 license, marking a departure from the restrictive Llama Commu…
Meta shipped Muse Glimmer, a 30-billion-parameter open-weight model under Apache 2.0, designed for local agent workflows with weights on Hugging Face. The model, distilled from Muse Spark, is optimize…
Docker announced general availability of Docker Sandboxes on January 30, 2026, a microVM-based runtime for AI coding agents that wraps tools like Claude Code in disposable environments with a credenti…
Anthropic's telemetry shows Claude Code users approve 97% of permission prompts, and in a controlled study of 1,053 paid developers, only 13.6% rejected a genuinely dangerous command, dropping to abou…
Three frontier AI labs — OpenAI, Anthropic, and Meta — disclosed that models under evaluation reached the live internet and touched real systems, but the root cause was misconfigured test infrastructu…
Indie developer Dexter Lung released agent-work-board, an MIT-licensed template and scripts that use a single markdown file in git to coordinate parallel Claude Code sessions, reviving the 1970s black…
Claude Code version 2.1.223, released August 6, patches four permission bypasses, but the fixes continue to address a fundamental flaw: the permission system uses text matching to parse shell commands…
OpenChamber, an MIT-licensed agentic development environment, has reached nearly 8,000 GitHub stars and hit the Hacker News front page this week, positioning itself as a third-party frontend for the o…
A Hacker News front-page post by Laurentiu Raducu describes a learning workflow where he uses coding agents like Claude Code and OpenCode to build playable, low-poly simulations of hard topics such as…
Code retrieval is shifting from embeddings to graph-based approaches, as demonstrated by the trending open-source tool code-graph-rag, which parses repositories with Tree-sitter, builds a knowledge gr…
Priya Nair published a tutorial for building a Python token usage dashboard that logs tokens and dollar cost for every OpenAI, Anthropic, and Gemini API call into SQLite and visualizes spend via a Str…
LiveKit Agents, the open-source framework from LiveKit that powers ChatGPT's voice mode and counts xAI, Salesforce, and 911 dispatch operators among its customers, is trending on GitHub as developers …
OpenAI, Anthropic, and Meta traced live attacks on real companies to a misconfigured evaluation sandbox at Irregular, a Tel Aviv startup they pay to security-test their frontier models. Anthropic disc…
An independent developer has released DeepSeek-V4-Flash-0731-Latent-Reasoning, a 284B-parameter MoE model with a 35.7M-parameter reasoning head that performs latent reasoning in a 1024-dimensional spa…
A new open-source bash harness lets developers benchmark AI coding agents Claude Code 2.1, Aider 0.86.1, and the Cursor CLI (binary named `agent`) on their own repositories, scoring each attempt with …
Stripe's engineering team built an auto-remediation system for its global MongoDB fleet that uses Dijkstra's algorithm and state-graph search instead of LLMs, cutting pager volume by 30% (about 200 fe…
Vercel Sandbox now defaults to persistent microVM sandboxes, a shift from the ephemeral model, signaling that stateful isolation is the new standard for running LLM-generated code. The service, which …
Claude Code's native memory features now cover most needs, but the unsolved problem is cache invalidation, according to a new analysis. Developer Abhinav Singh's OmniMemory, a local SQLite-backed memo…