Full-text search across 70902 articles. Combine with topic and date filters; results sorted by relevance.
A developer building parallel coding agents found that relaying messages between sessions via copy-paste loses provenance and resembles prompt injection, so they replaced it with references to committed artifacts. They t…
Drive9 released v0.10.0, a cloud filesystem designed for AI coding agents, providing persistent file storage across sessions, tools, and machines, with support for E2B Cloud Sandboxes and Firecracker MicroVMs. The tool e…
OpenAI's Codex repository commit 5bcd7b0 adds hidden 'Daybreak Blue' and 'Daybreak Red' cybersecurity model definitions, refreshing model capabilities, instructions, plan availability, and service-tier metadata. The comm…
Matt Webb, creator of Galactic Compass 2, said he used ChatGPT as an interactive tutor to learn quaternions for the app's new augmented reality mode, rather than having the AI write the code. Webb noted that outsourcing …
A user identified as zayed-369 posted on the Hugging Face Forums on August 21, 2026, asking for a free AI API platform for chatting, code generation, and image creation. The post, categorized under 'Beginners', seeks rec…
NVIDIA's AVO coding agent scored 100% on the ARC-AGI-3 interactive reasoning benchmark, completing all 183 levels across 25 public environments without instructions or explicit goals.
A new list ranks the most influential thought leaders in agentic engineering, AI, and vibecoding, with Anthropic's Claude Code, Microsoft's MarkItDown, and OpenAI's Codex CLI among the top tools. The list, compiled by an…
Open-weight models have significantly narrowed the performance gap with closed proprietary models on general reasoning and coding benchmarks, though closed models still lead on the hardest reasoning tasks. This shift is …
ADWEEK's Brandweek conference will return to Atlanta from Sept. 15–17, 2026, featuring marketing leaders from Coca-Cola, Starbucks, Crocs, Mattel, Ben & Jerry's, and State Farm, with a full day dedicated to AI. The event…
Anthropic is preparing to roll out a new safety system for its top models that will let enterprise customers keep data on their own infrastructure, with safeguards and monitoring provided by Anthropic's automated systems…
A developer found that DSPy's compiled programs re-send up to 20 few-shot demonstrations on every inference call, adding significant token overhead that is invisible in the source code. The default optimizer attaches 4 b…
Plainspeak, a new open-source plugin, bans AI-typical words like 'delve' and 'leverage', filler phrases, and em dashes from AI agent responses to make them sound human. The tool, available via npm and for opencode, Claud…
RunAI Coder, a new AI-powered coding tool, claims to have merged 968 pull requests in one week from a single user, and offers pay-as-you-go metered API access with up to 6x savings through proprietary compression and bil…
GitHub's monthly commits doubled from 1.4 billion in April to 2.9 billion in August, according to the company's outage postmortem, which attributed the surge to AI agents generating code at machine speed. The 2.9 billion…
Researchers at an undisclosed institution introduced Reliable Neural Collapse approximation (ReNC), a method for Open-World Test-Time Adaptation (OWTTA) that uses neural collapse as a structural prior to filter out-of-di…
Researchers introduced RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation, achieving state-of-the-art zero-shot performance across eight public benchmarks. RecPFN is pretrained en…
Researchers introduced VGI-bench, a benchmark with 27 tasks and 810 instances for evaluating visual reasoning in video generation models, finding that even the strongest model, Seedance 2.0, achieves only 51.0% accuracy.…
Researchers introduced BERT-LER, a BERT-style model for coded electronic health records (EHRs) that encodes laboratory test results as discrete tokens via percentile-based binning and integrates Integrated Gradients for …
OpenAI's Codex CLI version 0.147.0 lacks explicit cache controls for GPT-5.6 Sol on Amazon Bedrock, causing cache-write tokens to account for about 85% of estimated spend, with 171.94 million cache-write tokens costing a…
Aurey AI's Studio tool focuses on the iterative loop of prompt-to-game creation, allowing users to describe an idea, play a generated version, and refine it through natural language feedback. The tool emphasizes playable…