Posts

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

Code Participation Statistics

Image
Source:  https://x.com/nichochar/status/2026344879517728908 What’s the bigger picture? New website creation is up 40% year over year. New iOS apps are up nearly 50%. GitHub code pushes jumped 35% in the US. All of these metrics were flat for years before late 2024. The graphs look like hockey sticks. People who have never written a line of code are building and launching software. Keep in mind, we can and should note that more quantity does not necessarily mean better quality. But the fact remains that the barrier to creating software has dropped dramatically, and that is a fundamental shift in the landscape of software engineering.
Post a Comment
Read more

What agentic development still requires from you

What agentic development still requires from you 1) Vision/Goal. AI will never tell you your goal.  Without the goal, how do you evaluate it is a success? 2) The current step. This is what most people set in their prompts.  Don't you think it is better to start with the vision and make the steps to reach the vision? 3) Clear requirements for each of the steps. If you cannot articulate what success looks like in a way that can be evaluated, no amount of autonomous execution will produce it. Agents cannot clarify requirements they are never given. They will fill the gaps with assumptions, and those assumptions compound. 4) Strong abstractions. An agent given a well-designed system with clear module boundaries, coherent interfaces, and good separation of concerns will produce better results than an agent given a tangled codebase where everything depends on everything else. Clean architecture is more important when agents are doing the implementation, because agents amplify the p...
Post a Comment
Read more

Gen AI Dev Exam

Gen AI Developer Exam    Integration approaches: 1) Bedrock integration (unified API), 2) AI Factories integration (on-premises), 3) SageMaker AI integration (self-host), 4) Direct provider API integration (direct API)   Nova Forge enables building custom frontier models, provides infrastructure and tools to create LLMs from scratch.    RAG components : 1) Doc processing: Chunks knowledge while maintaining context, 2) Embedding models: Converts text to mathematical vectors, 3) Vector storage: Efficiently stores and searches vectors, 4) Query processing: Matches user questions to relevant content, 5) Response generation: Combines retrieved context with queries    Nova tiers : Nova 2 Pro for complex tasks, Nova 2 Lite for cost-effective use cases, Nova 2 Sonic for real-time conversations, and Nova 2 Omni for multimodal capabilities. Data encryption:   Encryption in transit : Bedrock auto encrypts all data in transit using TLS 1.2+ via HTTPS ...
Post a Comment
Read more

Plate adjustments

  Plate adjustments https://www.youtube.com/watch?v=Pp9MwZkHiMQ https://github.com/bennjordan/PlateShapez
Post a Comment
Read more