Posts

AIs: LangGraph, Ollama, etc.

AIs: LangGraph, Ollama, etc.     LangGraph is the orchestration harness for LangChain agents.     Ollama is an open-source tool and framework designed to run, manage, and orchestrate various LLMs locally.  Ollama allows you to download and run dozens of different open-weight LLMs, including Meta's Llama, Alibaba's Qwen, Google's Gemma, and Microsoft's Phi. Ollama requires LLMs to be quantized into the GGUF format (the format used by llama.cpp) and configured with a Modelfile. Ollama does not fine-tune LLMs.   LLMs - usually in safeTensor or .gguf file format.  The .gguf file format is for local use.   Fine-Tuning =>  LLaMA-Factory is currently the most popular tool for local fine-tuning, because it provides a complete Web UI. You do not need to write any code to use it. It supports exporting trained models directly into the GGUF format needed for Ollama.   The NVIDIA DGX Spark  (custom Linux OS) and  R...
Post a Comment
Read more

Kimi K3 - Moonshot AI

Kimi K3 - Moonshot AI  Source:  https://www.tomshardware.com/tech-industry/artificial-intelligence/moonshot-releases-2-8-trillion-parameter-kimi-k3 Beijing-based Moonshot AI has released Kimi K3, a 2.8 trillion parameter model that the company describes in its technical blog as the world's first open 3T-class system and the largest open-weight AI model to date. Moonshot said K3 still sits behind Anthropic's Claude Fable 5 and OpenAI's GPT 5.6 Sol on overall performance, but it outperformed every other model in the company's evaluation suite, including Claude Opus 4.8 and GPT 5.5, across coding and agentic benchmarks. The model has a 1 million token context window... Moonshot claims roughly a 2.5x improvement in scaling efficiency over Kimi K2, attributed to two architectural changes: Kimi Delta Attention, a hybrid linear attention scheme, and Attention Residuals, which change how information moves between layers. 
Post a Comment
Read more

Github's Squad - orchestrator

Image
 Github's Squad - orchestrator Code:  https://github.com/bradygaster/squad Github has a fleet of agents in the Githob CLI. Subagents in the Fleet sphere are dumb and have no memory and do not learn. No specialized training, history, etc. 18% to 20% better if given individualized tasks to do with specialized training.  Also, they do better since they do not fight over duplicate tasks or have to do merging.   Team of Agents Squad Coordinator Routes work, enforces handoffs and reviewer gates. Does not generate domain artifacts. Which Agent Does What Expected Output After Each Agent Runs
Post a Comment
Read more

Autonomous AI

Image
 Autonomous AI Source: https://www.youtube.com/watch?v=Y1aAy3jpQnY&t=943s Autonomous AI - "Bob" Our OpenClaw agent ("Bob"): Bob's website: https://bobrenze.com/ Bob's blog: https://blog.bobrenze.com/  Bob's book: https://a.co/d/014kieQI AI Stages Stage 1 - Assistant Communicator . So chatbot, assistant, 1 step at time, then look at results.        ChatGPT - https://chatgpt.com/        Claude Chat - https://claude.ai/ Stage 2 - Agent Collaborator. So CoWork agent, 1 task (multi-step) at time.       GitHub Copilot - https://github.com/features/copilot      Claude Code - https://claude.com/product/claude-code OpenAI Codex - https://openai.com/codex/ Stage 3 - Workflow Supervisor. So supervising the agent, sub agents do, hand off task. LangChain / LangGraph - https://www.langchain.com/langgraph Microsoft Agent Workflows - https://learn.microsoft.com/en-us/age... Stage 4 - Autonomous Manager. So go...
Post a Comment
Read more

AI models that are open

Image
AI models that are open  Background   AI models that are "open" tend to be open-weight models (with model parameters (weights and biases) and the inference code to run it) that you can download to your local environment and run it, instead of OSAID compliant open-source.  Open AI models are popular due to the ability to "fine tune" (customize or adapt) them to your specific purpose, rather than being more general purpose.  Fine tuning a model is the process of setting some new hyperparameter values and giving a trained model a new, specialized dataset and retrain it so it creates a new model with new weights.  (Usually followed by "model merges" (combines the two models together) and shrinks the model (by compression (like GGUF, AWQ, or EXL2) to reduce the precision of the weights (e.g., converting 16-bit numbers into 4-bit numbers)) for use on home computers.  Executive Summary    America's main open models are Meta's Llama and Google's Gemma....
Post a Comment
Read more

Claude Code source code leaked via Github

Claude Code source code leaked  via Github      On March 31, 2026, the full source code of Anthropic's Claude Code CLI was leaked via a .map file exposed in their npm registry. https://github.com/tanbiralam/claude-code Surprising Info Revealed in the Code  * Written by AI:  half a million lines of Typescript Javascript (Bun) code written almost entirely by Claude itself.  * "Undercover Mode": The code revealed a hidden, 90-line feature that activates when Anthropic employees contribute to open-source projects. It is designed to strip all traces of AI involvement, ensuring commit messages and pull requests do not reveal their AI origins or leak internal project codenames.  * Unshipped AI Features: The codebase contained references to highly advanced features still in development. This included "Kai ROS" (an always-on, autonomous background agent designed to work on GitHub issues while you sleep), "Ultraplan" (which spawns a heavy-duty remote Opus...
Post a Comment
Read more

PyPI Trusted Publishing

PyPI Trusted Publishing    PPTP is an auth method that allows CI/CD platforms to publish software packages directly to the Python Package Index (PyPI) without using long-lived passwords or API tokens. Instead of storing sensitive credentials in your code repo, this feature leverages the OpenID Connect (OIDC) standard to establish direct machine-to-machine trust between PyPI and your build environment. Since this GitHub Action is Docker-based, it can only be used from within GNU/Linux based jobs in GitHub Actions CI/CD workflows.  Source: https://github.com/marketplace/actions/pypi-publish  Docs: https://docs.pypi.org/ How It Works   The tool replaces manual secret management with an automated cryptographic exchange:   1) Pre-configuration: You link your specific code repository and workflow to your project settings on PyPI.  2) Identity Verification: When a deployment triggers, your CI/CD platform sends a short-lived OIDC identity t...
Post a Comment
Read more