Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A developer found that a manual checkpoint in a prompt chain outperformed full automation by 35 percentage points. After a 7-step automated chain for ad copy failed silently at step 6 due to ambiguous input, the develope…
The Java ecosystem is formalizing AI in production with stable contracts. LangChain4j provides a Java-native LLM orchestration layer with declarative annotations and seamless integration with Quarkus and Spring Boot. RAG…
A developer built an adapter that converts LangGraph agent event streams into OpenAI-compatible Server-Sent Events, enabling tools like Open WebUI to display a 'thinking' panel showing the agent's tool calls in real time…
Anthropic announced Claude Tag, a new feature for its AI assistant Claude that integrates deeply into Slack as a virtual coworker. The feature, available in beta for Team and Enterprise plans starting Aug. 3, allows Clau…
AI startup Legion is suing the U.S. government after Anthropic removed its Claude Fable 5 model from public access, complying with an export control directive. Legion claims the loss of the model caused immediate, irrepa…
A developer shared three ready-to-use AI loop templates that enable AI to self-correct and produce finished work without human intervention. The loops rely on countable, pass/fail goals and have been used to catch repeti…
A writer proposes using emojis to passive-aggressively shame people who use large language models selfishly, such as by generating AI-written messages that waste others' time. The method includes dog-whistle emojis like …
A developer built an open-source repository of custom instruction bundles called angular22-agent-skills to prevent AI coding assistants like Cursor, Claude Code, Windsurf, and GitHub Copilot from generating legacy Angula…
Nous Research announced that its Hermes Agent can now learn from any source material, including code, API docs, manuals, PDFs, and configs, distilling them into verifiable reusable skills.
The Associated Press reports that users like Marie Lansley are increasingly turning to AI chatbots such as ChatGPT, Claude, Grok, and Gemini to draft messages and interpret replies on dating apps, raising concerns about …
The AI safety community outside frontier labs, termed 'outsiders,' is expected to play a key role in ensuring a positive transition to artificial superintelligence, according to an analysis. Outsiders are well-suited for…
Anthropic shipped Claude Tag on June 23, a persistent AI teammate for Slack that builds organizational memory and can work autonomously. The tool replaces the existing Claude Slack app with a hard migration deadline of A…
A developer has created a working solution to run AlecaFrame, a Warframe companion app built on Overwolf, with Warframe on Linux using umu-launcher and Proton without Steam. The setup enables live data tracking of invent…
A developer connected Claude's Model Context Protocol (MCP) to an enterprise identity database, enabling natural language querying of operational data. The system uses dynamic schema discovery and a secure SQL validation…
Zhipu AI released GLM 5.2, a 744-billion-parameter mixture-of-experts open-weight model that outperforms Claude Opus on visual design tasks at lower cost. The model features a longer context window, improved vision-langu…
Sakana AI launched Fugu, a multi-agent AI system that orchestrates Claude, GPT, and Gemini through one API to outperform individual frontier models on benchmarks. The system uses a mixture-of-agents approach, routing pro…
Microsoft Principal Developer Advocate Waldek Mastykarz published a blog post arguing that testing large language models in empty chat sessions is methodologically flawed, as models have no preferences—only context. The …
Anthropic's Claude Code, paired with the Gmail MCP server, enables users to build a skill that automatically reads inbox newsletters, scores AI stories, generates a ranked digest, and drafts LinkedIn posts each morning. …
Anthropic's Claude Code introduces five effort levels—Low, Medium, High, Max, and Ultra Code—that control the thinking token budget for reasoning before acting. The /effort command allows users to match computational eff…
Anthropic's Claude Code introduces a /goal command that lets AI agents run until measurable conditions are met, preventing premature stops by defining verifiable finish lines. The command creates an outcome-based feedbac…