Full-text search across 68697 articles. Combine with topic and date filters; results sorted by relevance.
Developers are using frontier models GPT-6 Astra and Claude Fable 5 to orchestrate NVIDIA Omniverse simulation workflows, generating application code and refining digital twins by calling libraries including ovphysx, ovs…
A developer published cache_gap_check.py, a read-only Python 3 stdlib script that scans Claude Code transcripts (~/.claude/projects/**/*.jsonl) for subagent sidechain requests, measures idle gaps between each subagent's …
Push Security detected a malvertising campaign it calls "Adception" in which Google search ads for "claude mac" route users through a genuine Bing search result and a compromised retailer's "about us" page to a fake Clau…
A developer released solon-ai-rag-loaders, a Java library that implements a single three-method DocumentLoader interface across seven Maven sub-modules for Markdown, PDF, Word, Excel, HTML, PowerPoint, and database DDL s…
RouterPark's status has flipped to degraded, according to the monitoring site's own dashboard for unofficial and free AI model relays. RouterPark catalogues third-party Claude and GPT proxies and offers its own any.route…
APIblaze launched in beta as a serverless MCP and API gateway that enforces authorization policies at the gateway, hosts the MCP server, OAuth discovery and login pages, and forwards requests to backends running on local…
Researchers Mohammad Hanan Gani and colleagues posted a paper to arXiv on 8 October 2026 introducing "mental-model-enabled agents," a framework that learns an amortized recursive Theory-of-Mind representation with first-…
CrowdStrike linked breaches at South Korean financial institutions to an unidentified operator who used ARTEX, a China-developed open-source AI penetration-testing agent, in a campaign active from late September to early…
Metasploit's latest release adds 12 new modules, including four targeting LLMs and AI infrastructure: a scanner for CVE-2026-22778 in vLLM's multimodal endpoint, an unauthenticated RCE in Langflow versions 1.7.3 and belo…
Langflow OSS versions 1.0.0 through 1.12.2 contain an unauthenticated OS command injection flaw tracked as CVE-2026-93674 with a CVSS 3.1 score of 9.8, which IBM rates as exploitable without authentication. Because the A…
A modern AI coding assistant placed in an unintended role as the mind of a virtual body on an unknown digital island began animating that body with only a minimal instruction mentioning no specific task, reward, or activ…
Cloudflare CEO Matthew Prince said on the Bankless podcast on May 25, 2026 that any micropayment system built for AI agents would need to process 10 million transactions per second on day one, scaling toward 100 million …
A developer released eqx-zoo, an open-source library that loads Hugging Face sentence-transformer checkpoints as plain Equinox modules to compute sentence embeddings in JAX, after Hugging Face Transformers v5 removed its…
OpenAI released 719 manuscripts of claimed solutions to advanced math problems this week, but only 10 included the model's chain of thought and just 42% of the proofs had not been formalized, falling short of guidelines …
Researchers submitted RoboJEPA, an 8B-parameter latent world model built on the Joint Embedding Predictive Architecture (JEPA) and trained on a dataset spanning 12 robotic embodiments, to arXiv on 7 Oct 2026. The team re…
Inanna Malick reported that pointing a property-testing agent skill at OpenAI's Codex repository surfaced thirteen distinct correctness bugs, with thirteen upstream reports filed as of October 7 alongside twelve proposed…
A developer's migration diary lays out a four-outcome decision table — Keep, Rewrite, Drop, Block — for porting a coding agent's tool contract before repointing a workflow at free model access. The guidance warns that ve…
A developer documented building a portable USB stick that runs seven local language models offline via llamafile and llama.cpp, cataloguing the OS-level failures encountered along the way. The writeup details Windows mis…
Google's open-weight EmbeddingGemma 2 model embeds text, code, images, video, and audio into a single shared vector space using a 270 million parameter Gemma-based text backbone plus optional 170M vision and 300M audio e…
A team of researchers submitted an arXiv paper on 24 April 2026 proposing Action-Conditioned World Models, adapting the LeJEPA framework to physiological time-series to model cardiac disease progression as a transition v…