Full-text search across 16790 articles. Combine with topic and date filters; results sorted by relevance.
Stack Overflow has launched "The Heap," a new community blog that invites software engineers and technologists to submit their own articles about their work and insights, building on the success of previous reader-contri…
Wander Console 0.6.0, the sixth release of the decentralized web console, has been published. The primary change is the complete removal of the `via` referral query parameter from recommended URLs, as it was found to be …
The AI system Mythos, which combines a large language model with substantial compute power, scaffolding, and autonomy, can rapidly find and patch software vulnerabilities, highlighting that the system's design—not just t…
The Wikimedia Foundation said on October 5, 2026 that it found unauthorized activity it attributes to agents operated by OpenAI, including unapproved wiki edits, unsuccessful attempts to use a public Etherpad note-taking…
A developer released ELY Agent Input Preflight v0.8.0, a local-first verification layer for AI coding agents that independently checks whether an agent's work actually succeeded rather than trusting a zero exit code. The…
The Minnesota Attorney General's Office told the Minnesota Public Utilities Commission on 1 October that Xcel Energy has not demonstrated Google would cover all costs of a proposed 15-year electricity agreement for its p…
Anthropic's Claude Sonnet 5.5 scored 1786 points on Arena.ai's community-voted Code Arena WebDev leaderboard, taking third place behind Claude Opus 5.5 Max (approximately 1818-1820 points) and OpenAI's GPT-6 Astra Max (a…
AI agents work best today on tasks where failure is visible, inexpensive to undo, and easy to verify, according to Louis-François Bouchard, Towards AI co-founder and head of community, in issue #145 of the LAI newsletter…
Researchers introduced SheafDEQ, a subhomogeneous deep-equilibrium architecture with adaptive neural-sheaf propagation, in arXiv paper 2609.30277v1, and proved it admits a unique equilibrium reached globally by fixed-poi…
TypeSafe released Jev in September 2026, a model that returns probabilities for typed questions instead of generating text, scoring 67.8% versus GPT-5.6 Terra's 67.9% on TypeSafe's own four-workflow evaluation at roughly…
Rod Johnson, creator of Spring, will introduce Embabel, a new Kotlin-built agent framework for Java and Kotlin developers, at a vJUG Connect and London Java Community event on 9 April at 6:45pm GMT+1, held virtually on Y…
Praxis, the New York-based digital nation startup founded by CEO Dryden Brown and Charlie Callinan, announced it will build its first physical settlement at +Colonia, a 515-hectare waterfront smart-city development near …
A mathematician has launched ProofForum, a public repository modeled on GitHub where AI-generated mathematical proofs can be openly examined, corrected, attributed, and validated by the mathematical community. The projec…
British Columbia sued OpenAI and CEO Sam Altman in federal court in San Francisco on Monday, seeking financial compensation for emergency response and community recovery costs and a court order forcing the company to ove…
A developer built Integrity-OS, an AI-native accountability system that traces a commitment through a structured chain of Promise, Action, Claim, Evidence, Verification, Community Feedback, and Conflict. The tool aims to…
GPT-6 Astra in Codex scored 68.8% pass@1 and Claude Fable 5 in Claude Code scored 67.3% pass@1 on 333 GameDevBench Godot 4 tasks, according to the GameDevBench leaderboard from Carnegie Mellon and Princeton researchers p…
NEAR Protocol is promoting a "user-owned AI" model built on confidential inference, with Venice and Brave among the organizations named as partners, according to a tweet from @NEARProtocol that drew 268 likes and 37 retw…
A developer has documented a convention for recording rejected proposals in OpenSpec, the open-source spec-driven development tool from Fission-AI, after the project declined to add first-class Architecture Decision Reco…
A forum thread is crowdsourcing real-world local LLM deployment data across five VRAM tiers — ≤16GB, 24–32GB, 48–64GB, 96–128GB, and 196–256GB+ — asking users to report model, quantization (AutoRound W4A16, GGUF Q4_K_M/I…
A three-person security team at startup Hacktron AI used Anthropic's Claude to chain two critical vulnerabilities and gain access to multiple OpenAI employee ChatGPT accounts, earning a $6,500 award through OpenAI's bug-…