Stories by fzysingularity

Build visual AI workflows from a prompt – OCR, detection, editing and more

How we solved multi-modal tool-calling in MCP agents – VLM Run MCP

video2json – Transcribe and analyze hours-long videos

Georgi Gerganov on X: "x2 speed for WASM by optimizing SIMD" / X

I'm Hooked on Devin ( Cognition_labs)

Ask HN: GPT4V and function calling use-cases

Silent voice messages transcribe to "Thanks for watching" on ChatGPT

Ask HN: What are people using to automatically catalog images/video today?

Ask HN: Which cloud provider offers AMD MI250/MI300?

Serving LLMs on a Budget

2024 predictions on the open-source LLM wars

Fly.io for Multi-Cloud?

The AI Stack for the 3rd Epoch of Computing

My Own AI Server Cluster

AGI-pack: Dockerfile generator for ML developers

Blog – Introducing Intrinsic Flowstate – Intrinsic

Building LLM Applications for Production

Chroma