A bitwise reproducible deep learning framework

Hacker News (score: 20)
Found: December 22, 2025
ID: 2832

Description

Other
A bitwise reproducible deep learning framework

More from Hacker

Show HN: Tascli, a command line based (human) task and record manager

Show HN: Tascli, a command line based (human) task and record manager `cargo install tascli`<p>Manages your own task and records in the terminal simply with tascli - tiny, fast and simple.

Fast trigram based code search

Fast trigram based code search

Langjam Gamejam: Build a programming language then make a game with it

Langjam Gamejam: Build a programming language then make a game with it

Show HN: Runprompt – run .prompt files from the command line

Show HN: Runprompt – run .prompt files from the command line I built a single-file Python script that lets you run LLM prompts from the command line with templating, structured outputs, and the ability to chain prompts together.<p>When I discovered Google&#x27;s Dotprompt format (frontmatter + Handlebars templates), I realized it was perfect for something I&#x27;d been wanting: treating prompts as first-class programs you can pipe together Unix-style. Google uses Dotprompt in Firebase Genkit and I wanted something simpler - just run a .prompt file directly on the command line.<p>Here&#x27;s what it looks like:<p>--- model: anthropic&#x2F;claude-sonnet-4-20250514 output: format: json schema: sentiment: string, positive&#x2F;negative&#x2F;neutral confidence: number, 0-1 score --- Analyze the sentiment of: {{STDIN}}<p>Running it:<p>cat reviews.txt | .&#x2F;runprompt sentiment.prompt | jq &#x27;.sentiment&#x27;<p>The things I think are interesting:<p>* Structured output schemas: Define JSON schemas in the frontmatter using a simple `field: type, description` syntax. The LLM reliably returns valid JSON you can pipe to other tools.<p>* Prompt chaining: Pipe JSON output from one prompt as template variables into the next. This makes it easy to build multi-step agentic workflows as simple shell pipelines.<p>* Zero dependencies: It&#x27;s a single Python file that uses only stdlib. Just curl it down and run it.<p>* Provider agnostic: Works with Anthropic, OpenAI, Google AI, and OpenRouter (which gives you access to dozens of models through one API key).<p>You can use it to automate things like extracting structured data from unstructured text, generating reports from logs, and building small agentic workflows without spinning up a whole framework.<p>Would love your feedback, and PRs are most welcome!

No other tools from this source yet.