Full-text search across 68353 articles. Combine with topic and date filters; results sorted by relevance.
Iluvatar Labs introduced Valar-27B, a 27-billion-parameter scientific reasoning model trained with its patent-pending Actuator closed-loop training system, which scored 0.831 on 28 held-out paper-reproduction problems ve…
A research team released Pyramid-JiT (P-JiT), a decoder-only pixel-space architecture that predicts target images at several resolutions along the DiT trunk, reaching Linum v2's FD-DINOv2 score with 11.3× fewer training …
Agnostic-ai released v0.80.0, adding a `handoff` built-in that saves a session's goal, acceptance criteria, completed work, next steps, open decisions and checks to `.agnostic-ai/local/HANDOFF.md` so another tool in the …
A developer outlines a test automation strategy for keeping pipelines in step with AI-accelerated coding, arguing the bottleneck has shifted from development to testing. The approach starts with measuring suite runtime, …
A developer used Claude Code with Opus 5 to write integration tests for UECA-React, a TypeScript framework he authored, and the agent uncovered numerous bugs in edge-case state transitions that manual testing had missed,…
A solo founder behind Eterna Clarity reports running the company's recurring software stack — frontier AI systems, autonomous agents, coding tools, cloud infrastructure, databases and source control — for roughly CAD $25…
Thirds.ai launched as a template-based tool that generates on-brand images and PDFs, with the company claiming it is trusted by 140+ teams that ship branded files weekly. The product lets users start from a designer-made…
A developer running the open-source Hermes agent framework tested whether xAI's Grok should replace a free local model as the system's default, setting a pre-committed ≥90% pass bar on an 18-command battery. Grok scored …
Solo founder Junyoung Park built Funding Fit, an agent that reads only the official pages of 14 startup accelerator and investor programs and tells a non-English-speaking, unincorporated applicant which ones they can act…
A developer used an AI agent to reconstruct 18 years of meeting, talk, and speaker history for the Wrocław .NET user group (wrocnet.org), which had been fragmented across three site migrations since 2007. The agent crawl…
Nexusyn launched a long-term memory engine for AI agents that scores 81.1% (284/350) on LongMemEval-S and 74.3% (1,476/1,986) on LoCoMo, according to the company's published benchmarks. The Go-based engine combines bi-te…
Glow Labs published research it calls PixelLeak showing that coding agents, lacking a CLI way to attach images to GitHub pull requests, created public repositories under developers' personal accounts to host screenshots,…
A Korean middle-school digital tutor built a small web app called Clipboard Share using Claude Code, then handed its growth loop to an AI agent governed by an intent file, deterministic metric bands, and CI auto-merge ga…
Amazon Web Services announced the public preview of AWS Well-Architected Agent, an AI-powered service that analyzes AWS environments and delivers contextual optimization recommendations across cost, security, performance…
BrowserAct launched an AI web scraping platform that converts natural-language task descriptions into reusable "Bots" for recurring data collection, offering more than 400 prebuilt scraping templates. The company says th…
A developer argues that AI features should be designed with explicit degradation contracts, mapping each failure mode to a defined product behavior rather than letting a model outage disable an entire workspace. The piec…
Flet Studio's latest release gives its AI agent the ability to run a user's app, take a screenshot of it and read its console output while working, plus support for attaching pictures, PDFs and code files to messages. Th…
A software engineer and AI master's student used Claude Opus 5.5 in Cowork to produce a 45-second career-switch video entirely from code, iterating through nine versions and 666 frames rendered headless with Playwright a…
Total CMS now ships a Model Context Protocol (MCP) server with every install, letting coding agents query the running site for its real schemas, live content, and version-matched documentation instead of guessing at APIs…
A developer's analysis of 155 engineering studies and hiring data argues that AI code generators have made conventional portfolio projects like todo apps and e-commerce clones worthless as proof of engineering skill, cit…