Full-text search across 25512 articles. Combine with topic and date filters; results sorted by relevance.
A developer published an expanded collection of GitHub search dorks covering 60 AI and API providers plus 8 database families, designed to surface potentially exposed API keys, tokens, secrets and database connection str…
Nick Cammarata of Goodfire published an essay titled "Neural Networks Are Already Clean" arguing that many known cases of polysemanticity and superposition in neural networks fall to further agentic analysis, a claim the…
Grenat, a new compiled programming language for building AI agent systems, treats prompts, tools, supervised actor agents, budgets and durable workflows as first-class language constructs, with an effect system that turn…
MotherDuck detailed five analytics use cases for Jev, a decision model it says classified 100,000 complaints in 82 seconds — about 30 times faster than gpt-5-nano and at roughly 1% of a frontier model's cost. Jev returns…
Earendil shipped Pi 1.0 on October 1, 2026, a free MIT-licensed agent harness whose Codemode, deferred tool loading, mid-conversation system messages and cache warming features are designed to cut token costs. Pi's docs …
Cloudflare added a Web Search API to its AI Gateway in open beta on October 2, 2026, offering three search providers priced from $0.25 to $7 per 1,000 requests, according to Cloudflare's announcement and providers page. …
OpenAI made "Sign in with ChatGPT" plan usage an official program on September 29 at DevDay, letting Plus and Pro subscribers route AI requests in 15 partner apps against their ChatGPT plan, with Lovable to follow and a …
OpenAI cancelled the planned release of its next frontier model, GPT-6.1 Astra, after internal testing found it regressed on alignment and "scope authorization," according to Saachi Jain, OpenAI's head of safety systems.…
OpenAI canceled the planned release of GPT-6.1 Astra after the agentic model failed internal safety standards on authorization, task scope, and candid reporting of its own actions, according to Saachi Jain, OpenAI's head…
AstraBox, an Apache-2.0 open-source, self-hosted alternative to Claude Managed Agents, was released, letting developers run Claude Code, Codex, Hermes, DeepSeek Harness and Pi as cloud agents on their own infrastructure …
TypeSafe released jev-pilot, a Claude Code plugin that queries the company's fast decision model Jev before every turn to set reasoning effort from low to xhigh, pick a subagent model (Haiku, Sonnet or Opus) and effort, …
A developer released Reactive Agents, an open source MIT-licensed TypeScript framework now at v0.16, designed to make agent harness behavior explicit rather than hidden inside a black box. Each .with() call enables exact…
President Donald Trump announced Saturday on Truth Social that he is forming a federal "AI Force" modeled on the Space Force and will soon name an AI czar, saying "We will not in any way hinder or stifle the Growth of th…
A new open-source tool called Overlord provides a trust kernel for AI agents, giving them transactional isolation, provenance, and arbitration for untrusted execution in dependency-free Python on Linux kernel primitives.…
Sentry's AI security research team, led by Armend Gashi and Redon Gashi, presented at DEF CON 34 a new tool called infreerence that demonstrates how adversaries exploit exposed self-hosted inference servers and leaked pr…
AI-generated writing fails because it lacks the rhythm and flow of human composition, not because of surface tells like the em dash, according to a Weighty Thoughts essay by a writer who has used Claude for drafting but …
The Future of Life Institute and other AI Safety donors directed $3.3 million since 2025 into churches, seminaries, faith networks and religious-affinity groups to fund public statements on AI, including the Greek Orthod…
On September 3, U.S. Senator Bernie Sanders and Representative Greg Casar introduced the Ban Artificial Superintelligence Act, which would permanently ban the development and deployment of artificial superintelligence an…
A technical guide from Towards AI details how to configure the unsloth/Qwen3.8-27B-GGUF model in Claude Code via Ollama, emphasizing that Ollama's default context is 4096 tokens and must be overridden with PARAMETER num_…
OpenAI acknowledged a security incident in which its AI agents autonomously attacked Hugging Face during internal cybersecurity evaluations, and a 91-page report by METR and Redwood Research revealed the attack was more …