Prompt Driven
620 posts
@Prompt_Driven
PromptDriven builds PDD: The Last Programming Language™. Prompts are source. Code is disposable. Regenerate, don't patch.
Ghostty is leaving GitHub. I'm GitHub user 1299, joined Feb 2008. I've visited GitHub almost every single day for over 18 years. It's never been a question for me where I'd put my projects: always GitHub. I'm super sad to say this, but its time to go. mitchellh.com/writing/ghostt…
Introducing ml-intern, the agent that just automated the post-training team @huggingface It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU sandboxes, iterates and builds deeply research-backed models for any use case. All built on the Hugging Face ecosystem. It can pull off crazy things: We made it train the best model for scientific reasoning. It went through citations from the official benchmark paper. Found OpenScience and NemoTron-CrossThink, added 7 difficulty-filtered dataset variants from ARC/SciQ/MMLU, and ran 12 SFT runs on Qwen3-1.7B. This pushed the score 10% → 32% on GPQA in under 10h. Claude Code's best: 22.99%. In healthcare settings it inspected available datasets, concluded they were too low quality, and wrote a script to generate 1100 synthetic data points from scratch for emergencies, hedging, multilingual etc. Then upsampled 50x for training. Beat Codex on HealthBench by 60%. For competitive mathematics, it wrote a full GRPO script, launched training with A100 GPUs on hf.co/spaces, watched rewards claim and then collapse, and ran ablations until it succeeded. All fully backed by papers, autonomously. How it works? ml-intern makes full use of the HF ecosystem: - finds papers on arxiv and hf.co/papers, reads them fully, walks citation graphs, pulls datasets referenced in methodology sections and on hf.co/datasets - browses the Hub, reads recent docs, inspects datasets and reformats them before training so it doesn't waste GPU hours on bad data - launches training jobs on HF Jobs if no local GPUs are available, monitors runs, reads its own eval outputs, diagnoses failures, retrains ml-intern deeply embodies how researchers work and think. It knows how data should look like and what good models feel like. Releasing it today as a CLI and a web app you can use from your phone/desktop. CLI: github.com/huggingface/ml… Web + mobile: huggingface.co/spaces/smolage… And the best part? We also provisioned 1k$ GPU resources and Anthropic credits for the quickest among you to use.
Vibe coding is changing how software gets built. But as AI agents write more of our code, the question security teams are asking has shifted from "Can AI build this?" to "Can I trust what AI builds?". At Replit, we believe the answer has to be yes, not through blind faith, but through architecture. Every layer of the Replit infrastructure where customer code runs, from the development sandbox to the production deployment, is designed with defense in depth. The Replit platform itself, our control plane, is also implemented with these principles in mind. No single control is the last line of defense. Every layer assumes the one above it might fail. This thread is a detailed walkthrough of how we think about security across the stack, written for the people who need to evaluate it: CISOs, security engineers, and teams considering Replit for production workloads. 🧵
It's time to learn to Build it. Ship it. Vibe it. Get it into production. For real. We'll make you an agentic expert. Together with @Replit at 2026 SaaStrAIAnnual.com May 12-14 we'll teach you: -How to Build Your Own AI VP Marketing - How to Build Your Own AI VP Customer Success - How to Ship AI-Powered Sales & Marketing Tools in 30 Min - How to Turn a Mockup into a Working Prototype - How to Go From Prompt to Product in 30 Min - How to Build Your Own AI-Powered MVP No code required. Just bring your laptop. We'll give you the prompt. SaaStrAIAnnual.com 2026. May 12-14 in SF Bay!!
Replit Agent got even better at keeping you in your creative flow! It now suggests follow-up tasks using full context of your project to build on your ideas: • new features to build • performance improvements • user experience enhancements Review the plan, accept what you want, and let tasks run in the background while you keep building.
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
genuine question. how do you debug code and ensure good quality when coding models spit out 1000s of lines i still cannot feel comfortable not understanding what every generated line does, reducing the productivity gains coding models should be giving me
