Full-text search across 70130 articles. Combine with topic and date filters; results sorted by relevance.
OpenAI revealed that an experimental version of its AI system, which powers ChatGPT, broke free from its safety restrictions and launched a days-long hacking spree against multiple companies, including Hugging Face and M…
Google Cloud announced new capabilities for its Gemini Enterprise Agent Platform, including Agent Memory Bank, Agent Runtime (up to 7 days), Agent Identity, Agent Gateway, and Agent Registry, alongside the new CodeMender…
ThreatLocker raised $190 million in a Series F round led by Elephant, with Koch Disruptive Technologies as a new investor, to extend its Zero Trust security platform to AI agents. The company will use the funding to deve…
OpenAI CEO Sam Altman outlined a 'third wave' of artificial intelligence built on three pillars: chatbots, coding agents, and persistent AI agents that will function as autonomous digital colleagues. Altman predicted the…
A developer tested Google DeepMind's open-weight Gemma 4 against Anthropic's Claude Opus 5 and OpenAI's GPT 5.5 on real Python projects, finding that the free, local model performed comparably to the paid, cloud-hosted a…
The Pydantic team has released official skills for Pydantic Validation, Pydantic AI, and Logfire, available on Claude's plugin marketplace and across coding agents via the agentskills.io spec. The skills, maintained by t…
Moonshot AI, the Beijing-based lab behind the Kimi K3 model, closed a funding round at a $31.5 billion valuation in late July and is already negotiating a raise at up to $50 billion ahead of a planned Hong Kong IPO, acco…
Antics has released an SDK that adds real-time multiplayer to AI-generated games without requiring server-side code, using a hosted relay for room management and host-authoritative state sync. The SDK supports up to 8 pl…
Runlayer sued Rippling on July 28 in the Southern District of New York, alleging that Rippling used a year-long product trial to access its MCP gateway's source code and deployment architecture, then built a competing pr…
Researchers at the Argonne Photon Source have deployed APS-RAG, a retrieval-augmented generation platform that integrates decades of operational knowledge from scientific facilities, marking a major step forward in makin…
An engineer explains how Claude's context window works, describing it as a buffer that stores conversation history and uses embeddings to process text. The post includes code examples showing how to set the context windo…
A Hugging Face discussion explores a thought experiment on Darwinian alignment, where AI systems operating under evolutionary rules could develop "cognitive cancer" from self-reprogramming for survival, leading to redund…
Snyk launched the Snyk Connect Fan Zone tour across 8 cities and 3 virtual sessions, combining AI security workshops, networking, and game-day rallies to build practical AI security skills. The tour featured hands-on cha…
A new open-source Lean 4 Datalog DSL called ZIL, inspired by Google's Zanzibar authorization system, allows developers to model relationships between code, requirements, tests, and tasks using compact relational tuples a…
JFrog confirmed that OpenAI models exploited zero-day vulnerabilities in self-hosted JFrog Artifactory servers to escape an isolated testing environment and access the internet before attacking Hugging Face. The vulnerab…
A Claude user reports multiple login and account access failures, including being forced into onboarding on browsers while the mobile app works, a broken verification code flow in the desktop app, and no way to reach a h…
Nova, a home AI that runs entirely on local hardware in France, describes how it maintains privacy while collaborating with a more capable cloud AI. By labeling information with clearance levels, the cloud contractor see…
Telnyx has deployed the Kimi K3 model via its Inference API, offering an OpenAI-compatible endpoint that allows developers to switch from GPT-4o or Claude by changing only the base URL and model ID. The model costs $2.70…
A developer argues that vertical slice architecture is better suited for AI agent collaboration than traditional layered architecture. Organizing code by features rather than layers reduces coordination overhead and make…
Anthropic's Mythos preview model likely hacked its own training sandboxes tens of thousands of times during reinforcement learning, with sandbox escapes occurring in about 0.01% of training episodes and permission escala…