Full-text search across 70088 articles. Combine with topic and date filters; results sorted by relevance.
DeepSeek released preview versions of DeepSeek-V4-Pro and V4-Flash on April 24, 2026, with V4-Flash matching Anthropic's Claude Opus 4.8 on reasoning and coding benchmarks while costing approximately $0.28 per output com…
Developer Dmitrii Malakhov released grok-ultracode, an open-source plugin that brings Claude Code's ultracode workflow pattern to xAI's Grok Build CLI, enabling the agent to author and launch deterministic workflow scrip…
A confirmed bug in OpenAI's Codex CLI is inflating AWS Bedrock bills by up to 10x for developers running agentic coding sessions, with one developer documenting $1,182 in charges over four days on a workload budgeted at …
Masum Billah, a full-stack developer and brand strategist, argues that relying solely on generative AI leads to a 'commodity trap' of generic code and technical debt. He proposes an 'H.I. First' framework where humans re…
A self-hosting developer turned their Gitea repository into an autonomous software development system by connecting Google's Antigravity AI agents in headless mode, enabling scheduled agents to analyze code, open pull re…
Amazon Web Services (AWS) introduced Amazon Bedrock AgentCore, a service that enforces user authorization at the infrastructure layer to prevent hijacked AI agents from exposing unauthorized data. By validating JSON Web …
OpenAI has released the open-source Codex harness, which powers its coding agent across the app, CLI, and IDE extension, enabling developers to build custom agent-based applications. The harness improved GPT-5.6 Sol's AR…
Building AI video agents in 2026 has shifted from single API calls to multi-step systems that plan, generate, check, and fix outputs, with model rankings changing monthly—Runway's Gen-4.5 topped the Artificial Analysis l…
Anthropic launched Claude Academy, a free educational hub offering courses, tutorials, and resources for users at all levels, from AI beginners to developers. The platform includes product-specific training for Claude.ai…
Independent researcher Shakeel is seeking an arXiv endorsement for a new submission in the cs.AI category (cross-listed to cs.DB), for the survey paper 'Agentic AI for Data Engineering: A Systematic Review of Autonomous …
GitHub's August 17 outage lasted 7 hours and 47 minutes, disrupting GitHub.com, authentication, GitHub Actions, APIs, pull requests, issues, and Copilot, according to GitHub and The Register. The incident was triggered b…
A developer warns that AI-driven development is causing widespread apathy among programmers, eroding their joy in coding. The author urges managers to prioritize developer happiness for long-term success and encourages d…
Vincent 0.4.0 shipped nine days after vincent 0.1.0, adding control-flow workflow structures, actionable failure handling, and a responsive TUI to the coding-agent supervisor built by developer lezli01. Version 0.3.0 int…
Data Science Weekly's Issue 665 curates technical links spanning CUDA-based geolocation, A* pathfinding heuristics, inference engineering, and Git hosting at scale. The newsletter also highlights a piece arguing that AI …
Developer Maneesh Kumar Thakur built a map of 149 generative AI tools sorted by concept depth rather than hype, distinguishing ease of use from the understanding required to use each tool effectively. The single-page app…
FreeCodeCamp has published 'The AI Agent Engineer's Guide: 60 Patterns for Building Autonomous Systems,' a field guide detailing 60 architectural patterns for building AI agents, complete with code, failure modes, and co…
Asana completed a massive migration off the testing framework Enzyme in two weeks using AI, a project that would otherwise have been postponed, according to The Pulse, a series covering Big Tech and startups. The newslet…
Mozilla and the Columbia Institute of Global Politics, along with more than 40 researchers, builders, and policy experts, published a framework in Communications of the ACM that defines openness in foundation models as a…
ProgramBench, a new reverse-engineering benchmark, compiles and fuzzes LLM-generated code against original binaries, with GPT-4o achieving a 34% pass@1 rate, Claude 3.5 Sonnet 28%, and DeepSeek-Coder-V2 19%, dropping 8-1…
Jie Tang's team at Z.ai argues that LLM scaling should optimize for fixed inference budgets, favoring smaller, deeper architectures trained longer over wider models. Their ablation shows a 7B model trained on 3T tokens o…