Full-text search across 70063 articles. Combine with topic and date filters; results sorted by relevance.
OpenAI's GPT-6 Astra model successfully completed tasks that previous models like GPT-5.6 Sol and Fable could not, according to early-access user Claire Vo, who demonstrated breakthroughs in ChatPRD's product intelligenc…
A widespread network failure disrupted OpenAI's ChatGPT, Anthropic's Claude, and SpaceXAI's Grok on Thursday morning, with Downdetector recording a sharp surge in complaints and OpenAI acknowledging elevated error rates …
A developer's guide demonstrates how to run a local large language model on older or modest hardware using Ollama, a tool that simplifies downloading and running open models. The tutorial covers installation, pulling sma…
OpenAI on Thursday unveiled GPT-6 Astra, an AI model with major advances in computer use, coding, cybersecurity, scientific research, and professional work, rolling out first to enterprise customers with Daybreak access …
ChatGPT users worldwide encountered 404 errors on the chatbot, its website, and OpenAI's coding tool Codex, with messages like "unexpected status 404 Not Found: Unknown error," even as OpenAI's status page showed "fully …
Meta Platforms Inc. released Muse Spark 1.3, its most powerful AI model yet, with Chief AI Officer Alexandr Wang saying it is competitive with Anthropic's Claude Fable 5.1 and better than OpenAI's GPT-5.6 Sol, particular…
LM Studio and Ollama users control text generation through sampling settings: temperature sets randomness, top-p and top-k trim candidate tokens, and min-p, a 2024 refinement from Nguyen et al.'s paper, maintains coheren…
Two days after OpenAI launched GPT-6 Astra, early independent benchmarks show the model's Intelligence Index score of 61 matches GPT-5.6 Sol, while its Coding Agent Index improved from 65 to 67, indicating modest gains o…
A developer has released BeatDesign, an open-source, local alternative to Higgsfield Canvas that any MCP-capable agent such as Codex, Claude Code, or Cursor can operate. The tool keeps projects and assets on the user's d…
A developer who built an AI chatbot using Claude Code argues that AI tools only improve skills if users continually increase the challenge, comparing static AI assistance to training wheels that never get raised. The dev…
NTU-led researchers released Puffin-World, a multimodal model that generates camera-controlled RGB and depth views for 3D point-cloud reconstruction, on September 2. The model, detailed by Kang Liao and nine co-authors, …
A developer proposes a 'directory-as-ID' pattern for making AI-agent capabilities discoverable, using the repository's directory structure as the canonical identifier. This approach simplifies governance by attaching ACL…
LINE Taiwan Developer Relations Team Lead Evan Lin built a LINE group buying bot demo that leverages the Messaging API's Edit and Unsend webhook events to synchronize backend order data with user edits. The bot, named 'S…
The author of the paper 'RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests' (arXiv 2608.27831) has requested that Hugging Face move or withdraw their Daily Papers submission because it ap…
A new technical reference guide outlines the shift from request-response LLM applications to production-grade autonomous agents in enterprise settings, emphasizing regulated industries such as financial services and heal…
A developer proposes measuring code review effectiveness by seeding known-defective changes, inspired by Margaret-Anne Storey's concept of cognitive debt. The method, akin to mutation testing, aims to detect when reviewe…
Meta Platforms Inc. released Muse Spark 1.3, its most powerful large language model to date, claiming it is now competitive with Anthropic PBC's Claude Fable 5.1 and better than OpenAI Group PBC's GPT-5.6 Sol in coding a…
Google unveiled Gemini 3.8 Flash and Gemini 3.8 Flash Cyber on Wednesday, claiming the new model is its best reasoning and coding model yet while maintaining the same speed and cost as its predecessor, Gemini 3.7 Flash. …
A developer compiled a list of 12 open source projects for developers, highlighting tools such as OpenWork for accessing 50+ LLMs, T3 Code for AI agent control, and Godot Engine for game development. The collection spans…
Anthropic released a reference blueprint, "Commerce Agents," for building shopping and merchant agents on its Claude platform, featuring two fictional agents (a shopping agent for customers and a merchant agent for staff…