Hacker News with Generative AI: AI Tools

Adobe's new AI tool can edit 10k images in one click (theverge.com)
Adobe is launching new generative AI tools that can automate labor-intensive production tasks like editing large batches of images and translating video presentations.
I built an Gemini powered AI that detects and fixes Python errors with reasoning (medium.com)
In the ever-evolving landscape of software development, automated tools that can help diagnose and fix code issues are becoming increasingly valuable. Today, I’m excited to share a project that leverages Google’s Gemini model to automatically detect and fix errors in Python code. This tool not only identifies issues but also provides reasoned explanations for its fixes, making it an excellent learning resource for developers.
Using LLMs and Cursor to finish side projects (zohaib.me)
Struggling to finish side projects due to limited time? In my latest blog post, I share how I improved my productivity using AI tools like LLMs and Cursor IDE. Learn to refine specs, bootstrap code, and iterate effectively to rapidly build and deploy your projects—even with a busy schedule.
Exploring Microsoft's Phi-3-Mini and its integration with tool like Ollama (pieces.app)
Discover Microsoft’s Phi-3-Mini and its seamless integration with tools like Ollama and Pieces, enhancing AI-driven workflows.
Show HN: Self-hosted gateway to access LLMs, Ollama, ComfyUI and FFmpeg servers (servicestack.net)
The Analysis Tool in Claude.ai (anthropic.com)
We're introducing the analysis tool, a new built-in feature for Claude.ai that enables Claude to write and run JavaScript code.
Support for Claude Sonnet 3.5, OpenAI O1 and Gemini 1.5 Pro (qodo.ai)
AI-driven software development requires access to the most advanced tools and models available. With rapid advancements in large language models, staying ahead means continually integrating cutting-edge technologies. That’s why we’re excited to announce Qodo’s platform support for four models, in addition to the existing support of GPT-4o.
Show HN: AI OmniGen – AI Image Generator with Consistent Visuals (aiomnigen.com)
Use OmniGen to create images with text prompts, image references, and subject-driven generation.
NotebookLM is quite powerful and worth playing with (twitter.com)
Notes on Using LLMs for Code (simonwillison.net)
I was recently the guest on TWIML—the This Week in Machine Learning & AI podcast. Our episode is titled Supercharging Developer Productivity with ChatGPT and Claude with Simon Willison, and the focus of the conversation was the ways in which I use LLM tools in my day-to-day work as a software developer and product engineer.
Torchchat: Chat with LLMs Everywhere (github.com/pytorch)
Compare 75 AI Models on 200 Prompts Side by Side (aimodelreview.com)
Show HN: We made glhf.chat – run almost any open-source LLM, including 405B (glhf.chat)
Tell HN: Claude now lets you publish apps you create with artifacts (ycombinator.com)
Show HN: A CLI that uses Claude to fix your code until the tests/builds pass (github.com/joseferben)
Show HN: Rubbrband – A hosted ComfyUI alternative for image generation (ycombinator.com)
Writer AI Studio: build apps fast on a full-stack generative AI platform (writer.com)
All ChatGPT Free users can now use browse,vision,data analysis,file uploads,GPTs (twitter.com)
Anthropic: Prompt Library (anthropic.com)