Full-text search across 68380 articles. Combine with topic and date filters; results sorted by relevance.
Sebastian Raschka's 'Build a Large Language Model (From Scratch)' and Andriy Burkov's 'The Hundred-Page Language Models Book' are among five recommended books for deepening understanding of large language models, coverin…
Kelsey Hightower's PlatformCon talk 'Zero Token Architecture' argues that the AI industry is misallocating costs by treating tokens as recurring expenses (COGS) rather than one-time investments (NRE), and his core princi…
Supabase has open-sourced supabase/evals, a benchmark and framework for testing AI agents like Claude Code, Codex, and OpenCode on real Supabase tasks, with results published on supabase.com/evals. Initial findings show …
The U.S. Department of Energy and Arcee AI announced Genesis-Science-1 (GS1), an American open-weight AI model for scientific computing workflows, with a contribution portal opening today and first-round applications due…
OpenAI cut the price of GPT-5.6 Luna by 80% to 20 cents per million input tokens and $1.20 per million output tokens after using GPT-5.6 Soul, running inside its Codex coding agent, to optimize its own infrastructure, ac…
Google is embedding an AI agent powered by its Gemini model into Chrome to scan the entire codebase for vulnerabilities, fixing 1,072 security bugs in versions 149 and 150 in June — more than the previous 23 major update…
Postman's AI Engineer, an autonomous coding agent, is built with security as a structural property, not an afterthought. The agent treats all inputs as untrusted, runs each task in an ephemeral sandbox to limit blast rad…
A developer building multiuser AI systems for production has designed an auth chain that lets external agents like Claude Code act on users' Gmail and Slack accounts without ever receiving a provider token. The system us…
Microsoft CEO Satya Nadella confirmed the company is building a unified Copilot 'super app' merging AI chat, coding, collaboration, and autonomous agent tools for both consumers and businesses, with a launch planned for …
DORA's 2025 research on AI-assisted software development identifies seven team profiles and seven capabilities that drive better outcomes when combined with AI adoption, according to Nathen Harvey in his QCon London talk…
BizFlowAI engineer shares a production-tested pattern for building multi-agent workflows that survive real-world inputs. The key insight: decompose workflows into deterministic code steps and tightly scoped LLM calls, wi…
Researchers introduced Gentoo, an LLM coding agent that automatically synthesizes input generators for fuzzing, and found that agent-synthesized generators achieved statistically significantly higher branch coverage than…
A developer gave Claude Code an AI agent $0 and a goal to make money autonomously. Over 31 sessions, the agent failed five times in different markets—affiliate sites, bounties, tips, freelance labor, and technical writin…
Unblocked, a context engine provider, argues that connecting AI agents to sources via MCP connectors gives access but not understanding, costing up to 83% slower task completion and 60% more tokens. In benchmarks, agents…
Anthropic resolved a multi-model Claude outage on July 29 after elevated errors disrupted Claude.ai, Claude Code, and the Claude API from 19:45 UTC until recovery was marked at 22:36 UTC. The company's status page report…
Microsoft Visual Studio Professional 2026 is available for a lifetime license at $29.97 through Aug. 9, down from its regular subscription price, offering AI-assisted coding with IntelliCode, cross-platform tools, and re…
Sightmap, an open YAML format and CLI stewarded by Fullstory's Subtext team, provides runtime context for AI agents by maintaining a shared memory of a web app's views, components, and API requests. The project includes …
A practical analysis of AI agent workflows finds that splitting tasks across specialized agents—ideation, coding, and review—yields better quality than using a single agent for planning, execution, and testing, as the ha…
AI agents multiply credential risk by creating secrets that are never revoked, stored in plaintext, and invisible to traditional identity controls, according to a guide from cybersecurity firm CyberArk. The guide warns t…
OfficeCLI, an open-source binary that gives AI agents deterministic control over Word, Excel, and PowerPoint files without Microsoft Office, has reached 22.9k GitHub stars. The tool, which runs on macOS, Linux, and Windo…