Show HN: Collection of skills to help improve UX and AI Product designgithub.com4 points·by tommyjepsen·il y a 10 jours·0 comments
Supervised vs. Unsupervised AI-generated codetommyjepsen.com2 points·by tommyjepsen·il y a 12 jours·0 comments
Learnings from Building an Ecommerce Chatbot for a Hardware Storetommyjepsen.com2 points·by tommyjepsen·il y a 2 mois·0 comments
Show HN: My Collection of UX / AI Design Claude Code Skillsgithub.com2 points·by tommyjepsen·il y a 2 mois·0 comments
Show HN: Cybersecurity Phishing Guard for Chrome using local LLMs for privacygithub.com2 points·by tommyjepsen·il y a 2 mois·0 comments
Show HN: UX Agent Mac app running continuously locally using Gemma 4github.com1 points·by tommyjepsen·il y a 3 mois·0 comments
Ask HN: What experience do you have with 'specs –> design –> code' orchestration2 points·by tommyjepsen·il y a 4 mois·0 comments
Show HN: I tried beating the stock market with Gemini 2.5 for 2025youtube.com2 points·by tommyjepsen·il y a 5 mois·0 comments
Blackstone's Jon Gray on AI as "The Main Thing", and Where to Invest Now [video]youtube.com1 points·by tommyjepsen·il y a 10 mois·0 comments
tommyjepsen·il y a 4 mois·discussI ran the Qwen3 Coder 30B through LM Studio and with OpenCode(Instead of Claude code). Did decent on M4 Max 32GB. https://www.tommyjepsen.com/blog/run-llm-locally-for-coding
tommyjepsen·il y a 5 mois·discussI got the Qwen3 Coder 30B running locally on mac Mac M4 Max 36GB. It was slow, but it worked and did do some decent stuff: https://www.youtube.com/watch?v=7mAPaRbsjTUVideo is speed up. I ran it through LM Studio and then OpenCode. Wrote a bit about how I set it all up here: https://www.tommyjepsen.com/blog/run-llm-locally-for-coding