News for hackers. Stuff that matters.

decodingchris

decodingchris on Hacker News

Re:GPT-6 Astra has gained the ability to drive a car on Wednesday September 23, 2026 @11:44AM (#49817838)
Super cool benchmark!
Re:Agora-1: The Multi-Agent World Model on Monday May 18, 2026 @03:06PM (#48184107)
Super cool!

Show HN: Prompttest – Pytest for LLMs

Posted by decodingchris on Monday August 25, 2025 @12:12PM
from the show-hn dept.

https://github.com/decodingchris/prompttest

I’ve been experimenting with LLMs lately and kept running into the same problem:Every time I tweaked a prompt, I had to rerun a bunch of test cases manually and eyeball the results.It felt like writing code without unit tests.Existing tools I found were either:- Full frameworks where you write evaluators in Python.- Big platforms expanding into monitoring/security.I wanted something simpler: a...

( Read More... | no comments | on HN )
Re:Launch HN: Jazzberry (YC X25) – AI agent for finding bugs on Wednesday May 14, 2025 @12:17PM (#43986305)
Cool demo! You mentioned using a microVM, which I think is Firecracker? And if it is, any issues with it?

Show HN: LatComp – Compress your image into a small and reversible format

Posted by decodingchris on Saturday November 30, 2024 @09:43AM
from the show-hn dept.

https://huggingface.co/spaces/decodingchris/LatComp

While taking the fast.ai course, I was learning about Variational Autoencoders (VAE) and began to wonder:Is it possible to represent the latent space as an image, and then reconstruct the original image from that representation?Well, here's the answer.

( Read More... | 2 comments | 3 points | on HN )
Re:Show HN: Free e-book about WebGPU Programming on Monday August 05, 2024 @09:22AM (#41161148)
Exactly what I was looking for! Thanks

Show HN: Blink – A Chrome Extension to Combat ADHD and Boost Focus

Posted by decodingchris on Saturday November 18, 2023 @08:46AM
from the show-hn dept.

https://chrome.google.com/webstore/detail/blink-effortless-focus/lhmfkleedadlmbjnhjpklndkhlkahkgp

Hello HN!I've just launched a new Chrome extension named Blink, which is inspired by a comment made by TheRealHB on HN. It suggests using a blinking LED to combat ADHD and maintain focus:https://news.ycombinator.com/item?id=38276107Blink replicates this technique by introducing a subtle, pulsating rhythm to your Chrome toolbar. The pulse begins at a quicker pace, similar to a rapid heartbeat,...

( Read More... | 1 comment | on HN )
Re:Hacking ADHD: Strategies for the modern developer on Friday November 17, 2023 @06:37AM (#38302154)
Thanks for sharing your hack! I made a chrome extension for myself and others that want to try it out. Would love your thoughts! https://chromewebstore.google.com/detail/blink-effortless-fo...
Re:Sharpen Your Communication Skills with an AI Conversation Simulator on Thursday June 15, 2023 @12:30PM (#36342984)
Hey HN!

This a video demo of an idea I'm working on. Basically, I'm using a few different AI models to create a conversation simulator.

The user gets to simulate any scenario with the ai. The goal is to help people practice their communication skills or important conversations in a "safe" environment.

Think flight simulators for pilots, but instead of flights, it's conversations.

Re:Discover ChatGPT's Hidden Capability: Visual Text Adventures in Fan... on Sunday June 04, 2023 @08:22PM (#36190859)
Nice! Did you encounter some repetition issues in your playthrough with 4 options?
Re:Discover ChatGPT's Hidden Capability: Visual Text Adventures in Fan... on Sunday June 04, 2023 @08:18PM (#36190842)
Nice find!

And yeah, repetition is an issue, there’s an instruction to not repeat story element in the initial prompt but it’s not working well. Any suggestions?

Re:Discover ChatGPT's Hidden Capability: Visual Text Adventures in Fan... on Sunday June 04, 2023 @07:41PM (#36190616)
Do you see the generated image and the discord link in Bing?

>>> import this

Posted by decodingchris on Sunday May 28, 2023 @11:34AM
from the self-post dept.

The Zen of Python, by Tim PetersBeautiful is better than ugly.Explicit is better than implicit.Simple is better than complex.Complex is better than complicated.Flat is better than nested.Sparse is better than dense.Readability counts.Special cases aren't special enough to break the rules.Although practicality beats purity.Errors should never pass silently.Unless explicitly silenced.In the face...

( Read More... | 1 comment | on HN )