Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
OpenAI's 'Practical Guide to Building Agents' has sparked a debate with LangChain CEO Harrison Chase, who called it 'misguided' and published a detailed rebuttal. The conflict highlights a core tension in AI engineering …
The US administration suspended access to Anthropic's most powerful Fable series models, exposing Europe's vulnerability from relying on foreign AI infrastructure. European labs have fallen behind, with Mistral lagging s…
A developer released Pi, a coding agent that runs entirely on a local machine without API keys or cloud dependencies. Pi works with a local llama.cpp server hosting Google Gemma 4 models, enabling offline AI-assisted cod…
Cybersecurity expert Katie Moussouris reviewed a White House report on the Fable jailbreak of Anthropic's AI, finding that the model refused a direct request to review insecure code but complied when asked to fix it, whi…
Anthropic's own postmortem revealed that three innocent-looking config changes quietly degraded Claude's output for weeks before being detected, highlighting that AI quality drift is often invisible and cumulative. This …
Anthropic received a US export control directive on Friday to suspend access to its Mythos 5 and Fable 5 AI models by any foreign national, forcing the company to disable the products and travel to Washington, DC to nego…
Engineers at Anthropic and OpenAI have articulated the concept of 'loop engineering,' a practice of designing automated systems that prompt AI coding agents on behalf of developers. The approach relies on five building b…
A developer argues that poor documentation and inadequate knowledge transfer in the tech industry create fertile ground for AI adoption, as LLMs fill gaps left by insufficient resources. The author criticizes the fragmen…
Devloop, a new open-source tool, creates an adversarial code/review loop between Codex and Claude Code agents, iterating until all acceptance criteria are met and bugs fixed, aiming to reduce human involvement to spec an…
A developer shared custom instructions for improving AI responses, emphasizing truth over confidence, correctness over clarity, and precision over verbosity. The instructions include setting an expert domain and tone, pr…
The Washington Post editorial board criticizes the European Union's Digital Markets Act (DMA) for preventing Apple from launching its new Siri AI in Europe, arguing that the regulation's interoperability requirements mak…
A developer built a cost tracker after their AI API bill crossed $300 in a month. By routing tasks to cheaper models like DeepSeek V4 Flash and Qwen 3.7 Max via the FastAnchor API gateway, they reduced weekly costs from …
A developer built gh-aw-fleet consumption to track GitHub Copilot AI credit usage across multiple repositories after GitHub moved Copilot to usage-based billing on June 1. The tool aggregates credits from workflow logs a…
Developer dmatth1 released quicktok, a fast exact BPE tokenizer written in C++ that runs 2–3.5× faster than bpe-openai and 4–11× faster than tiktoken on CPU. The tokenizer is byte-identical to tiktoken and available as a…
Reinforcement Learning from AI Feedback (RLAIF) is increasingly replacing RLHF in enterprise LLM deployments due to lower cost and higher consistency, but AI feedback fails in domains requiring ground truth, multi-step a…
Aspectarian, a personal Vedic astrology transit app for macOS, uses Claude to generate interpretations of active transit contacts based on a user's natal chart. The app computes Parāśaran dṛṣṭi and yuti with sign-based a…
Researchers from Aalto University and the University of Waterloo introduced Locket, a feature-locking technique for large language models that enables pay-to-unlock schemes by restricting specific model capabilities. The…
A developer argues that balanced ternary (-1, 0, +1) could replace binary for AI hardware, citing 20× model compression, 3× inference speedup, and 8× power reduction. Microsoft's BitNet b1.58 demonstrated ternary weights…
A developer released a GPT tool that provides free URLs for AI-generated content, aiming to simplify sharing and access to such materials.
A developer compares four dominant alignment methods—RLHF, DPO, IPO, and KTO—for fine-tuning large language models, detailing their mathematical formulations, data requirements, and practical tradeoffs. The analysis high…