News for hackers. Stuff that matters.

tommyjepsen

Show HN: Cybersecurity Phishing Guard for Chrome using local LLMs for privacy

https://github.com/tommyjepsen/local-llm-phishing-guard-for-chrome

Hi,I've been experimenting a lot with applications for local LLMs.This one makes a ton of sense, and might even be native in Chrome at some point.It's a Chrome Extension, that takes each new page automatically or manually and runs it through a local run LLM model.We look for 6 different signals, to try to identify if its a potential phishing attack or not.Local LLM because of privacy.I've...

( Read More... | no comments | 2 points | on HN )

Show HN: UX Agent Mac app running continuously locally using Gemma 4

https://github.com/tommyjepsen/ux-agent-app

Created an app that uses the Gemma 4 26B(only 18gb) model locally on my Mac, to support me as a UX Agent continuously evaluating my work and giving me feedback and pointers on where to improve.It takes a screenshot, analyzes it through its Vision capabilities and returns historical-related feedback in under ~6 seconds. The smaller models even faster.All done locally, privacy-friendly and...

( Read More... | no comments | on HN )

Ask HN: What experience do you have with 'specs –> design –> code' orchestration

Hi,We are currently researching automating a lot of the 'specs -> design -> code' pipeline with AI cloud agents.Basically, we make new tasks in Notion that are shaped by a human through a /shaping skill, that then gets picked up by an AI Agent doing a design prototype with our design system and all that.Here we add a designer/ux/pm/dev to see if the results are good enough, and then it...

( Read More... | no comments | 2 points | on HN )
Re:How to run Qwen 3.5 locally on Sunday March 08, 2026 @06:42AM (#47296228)
I 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
Re:Qwen3-Coder-Next on Tuesday February 03, 2026 @01:52PM (#46875445)
I 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=7mAPaRbsjTU

Video 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

Show HN: I tried beating the stock market with Gemini 2.5 for 2025

https://www.youtube.com/watch?v=fFncuUvnOKc

Hi,I ran a fun experiment trying to beat the danish C25 index with just Gemini 2.5 in simulation.I fed Gemini 2.5 with stock data, danish news articles, Wikipedia & Google trends top lists and much more like Eurostat data to see if I could get Gemini to beat the danish C25 stock index. (Novo Nordisk, Carlsberg, Mærsk etc.)It could only see the current days data and backwards and was...

( Read More... | no comments | on HN )
Hello,

I didn't find a decent priced solution to add subtitles to my videos, so I ended up exploring how to use Whisper and FFMpeg to do it and found a pretty decent solution, that is both free and fast.

Hope someone else can benefit from it to

Re:Show HN: I Made a Simple Tailwind CSS Quiz Game on Tuesday August 13, 2024 @05:28AM (#41233784)
Hi,

To advance my Tailwind CSS skills, I made a little quiz game to help me remember e.g. the height of h-48, how add line height etc.

Thought maybe others would find it funny as well and potentially help them become better at Tailwind :)

Show HN: I made a Bento Grid animation tool

https://motiongrids.com

Hi HN,I've developed a simple tool to animate and design Bento Grids from scratch to final mp4 file.I was as a product designer struggling in my job to create these Bento Grids using Figma and After Effects, so I made this tool to solve my own pain and thought maybe others would like it too.It is using React, Vite, FFmpeg, Shadcn, Tailwind, Firebase, Cloudflare R2 and lots of other cool libs...

( Read More... | no comments | on HN )
Hey! Yea, for mp4 its just ffmpeg -i and nothing else .. Good idea to optimize this. In general ffmpeg-wasm is a lot slower than FFmpeg run on your desktop, but let me see if I can improve on this.

Performance diff: https://ffmpegwasm.netlify.app/docs/performance

Hey, thanks for the feedback.

Yea makes sense with file naming and button. Let me try to iterate on that.

The mp4 to webm was actually the hardest to get working. Seemed like FFmpeg-wasm would stall at different times with some settings. I've updated it now to produce a bit better quality, but will definitely keep improving on this.

Re:Show HN: Shadcn website blocks you can copy/paste on Tuesday April 09, 2024 @07:54AM (#39978477)
Thanks! Had to move them, so they can be found in https://github.com/tommyjepsen/twblocks/tree/main/blocks now, but the website is also available to directly copy the code and inspect each block, so you don't have to go to Github anymore :)
Re:Show HN: Shadcn website blocks you can copy/paste on Tuesday April 09, 2024 @07:53AM (#39978466)
Not 100% sure what you mean, but maybe it is what https://ui.shadcn.com/blocks is doing?
Re:Show HN: Shadcn website blocks you can copy/paste on Tuesday April 09, 2024 @07:51AM (#39978456)
Hi, thanks! I've tried updating it to make it more user-friendly, so ppl don't have to go to Github to copy the blocks, but can do it directly on the website :)

Makes more sense this way.

Re:Show HN: Shadcn website blocks you can copy/paste on Tuesday April 09, 2024 @03:16AM (#39976904)
Hi, thanks! Yes, I've gotten this feedback from different places now - will definitely iterate on this. Right now you go to the Github repository: https://github.com/tommyjepsen/twblocks/tree/main/components and find the one you need.

Older »