Full-text search across 69244 articles. Combine with topic and date filters; results sorted by relevance.
Cantelop runs each active AI agent Session in a separate Firecracker microVM, isolating compute, host, network, resources, and lifecycle to limit the blast radius of untrusted code, according to a blog post by Stepan Ars…
A developer behind the independent project AI Change Watch found that a SQLite freshness query returned 1,252 crawl runs for the last hour when the true count was 68, because SQLite's datetime() emits a space at position…
A new security study found that four gatekeeper AI models approved 100 percent of crafted prompts that hid malicious instructions inside ordinary prose, even though each model had blocked the same requests when written i…
Microsoft researchers Li Dong and colleagues introduced YOCO, a decoder-decoder architecture for large language models that caches key-value pairs only once, in an arXiv paper submitted 8 May 2024 and revised 9 May 2024.…
Anthropic published findings alleging that Moonshot AI and DeepSeek secretly routed customer requests to Claude and passed Claude's answers off as their own models' output, with Anthropic attributing more than 23 million…
A developer released Feature Ledger, a command-line tool that automatically tracks features implemented in a software project by storing JSON descriptions in a .ledger directory. The tool offers commands including ledger…
A developer published a Claude Code PreToolUse hook that inspects the session transcript to detect whether the active model is a "fable" model and, if so, blocks the parent session from editing files via Bash commands su…
A 29 July 2026 arXiv paper by Aleksandr Berdnikov reports that most open-source language models of roughly 100B parameters hold a decodable representation of the night sky map in their residual stream, with the represent…
Details.so launched a handpicked website-design inspiration gallery that captures individual interface details — hero sections, footers, page transitions, preloaders and micro-interactions — from live production sites, t…
AT&T has shifted roughly 40 percent of its AI usage to open-weight models, up from 20 percent in May, according to chief data and AI officer Andy Markus, cutting costs by as much as 80 percent for high-volume tasks like …
Netlify has integrated with Cursor's Origin Git hosting platform, letting Origin repositories build, preview, and deploy on Netlify the same way GitHub, GitLab, and Bitbucket repositories do. The integration is in beta a…
A developer built a dependency-free Node.js SEO generator to stop an AI coding agent from hand-duplicating metadata across a 20-file multilingual static site for a North Cyprus property listing site. The tool's --check v…
A technical breakdown of how tokenizer training data skewed toward English — with English and code making up 95% of Llama 3's training data — creates measurable cost, context-window, and accuracy penalties for other lang…
A September 9, 2026 arXiv paper introduced IdeaAMBIG, a benchmark of 660 evidence-grounded instances — 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps — for measuring…
A CEO built an AI chief of staff using Claude Code that handles roughly half the workload of a full-time chief of staff within its first week and costs no more than $25 in tokens per day, less than 5% of a full-time hire…
Microsoft's PyRIT (Python Risk Identification Tool), launched in early 2024, has matured into a production-grade open-source AI red teaming platform used to red team hundreds of generative AI products and services, the c…
A prefix-cache simulator replaying 68,266 requests from 393 real Claude Code sessions and 23,608 Mooncake requests failed to beat the production LRU baseline in three separate attempts, according to the study's author. T…
A developer argues that front-end code longevity is a legibility property rather than a technology property, contending that systems survive when a stranger can reconstruct why decisions were made from the artifact itsel…
Teams building AI features should architect for portability now because current AI service pricing is heavily subsidized and will eventually rise, according to an analysis of AI vendor lock-in. The analysis recommends ro…
DeepSeek released V4.1-Flash, an efficiency-focused model with 552 billion total parameters (8 billion active for input, 16 billion for output) that matches or beats GPT-5.6 Sol and Claude Opus 5 on several agentic and c…