Hacker News Reader

jinayon Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Timestamped link to the YouTube video: https://youtu.be/T08wc4xD3KA?t=124

jinayon Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Ooh I haven't, but this is exactly the kind of follow-up I was looking for. Thanks for sharing!

jinayon Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

I recently did a deep dive on open-endedness, and my favorite example of its power is Picbreeder from 2008 [1]. It was a simple website where users could somewhat arbitrarily combine pictures created by super simple NNs. Most images were garbage, but a few resembled real objects. The best part is that attempts to replicate these by a traditional hill-climbing method would result in drastically more complicated solutions or even no solution at all.

It's a helpful analogy to understand the contrast between today's gradient descent vs open-ended exploration.

[1] First half of https://www.youtube.com/watch?v=T08wc4xD3KA

More notes from my deep dive: https://x.com/jinaycodes/status/1932078206166749392

jinayon Quarkdown: A modern Markdown-based typesetting system

Soon we'll start having a humans.txt format to account for this

https://xkcd.com/927/

jinayon Quarkdown: A modern Markdown-based typesetting system

Please add an llms.txt file! https://llmstxt.org/

I'd love to see how far I can take this by giving it to an LLM and asking it to format for me with Quarkdown.

jinayon Programming on 34 Keys (2022)

https://github.com/JinayJain/dictator

Built one for myself. It's context-aware and promptable.

Tested well on Linux, not so much on other platforms but in theory should support them.

It's a bit meta but I wrote it mostly using Claude Code. Once I had an MVP, I was able to prompt much faster by just speaking out what I wanted it to change.

jinayon Programming on 34 Keys (2022)

I used to think that typing speed was not really that important, especially when now we have so many LLMs doing the typing for us. But honestly, now I think it's even more important because the specificity and detail in your prompts are paramount to getting a good response, and something like a dictation tool (which is what I'm using right now) is really good for generating very specific prompts.

In fact, I wrote all this out using a dictation tool in ~20 seconds (258 WPM).

jinayon OpenAI to buy AI startup from Jony Ive

Went in an incognito window and searched "io" and this announcement was shown right above Google IO [1].

[1] https://i.imgur.com/xNKjFXa.png

jinayon OpenAI to buy AI startup from Jony Ive

I'm more referring to launch timing

jinayon OpenAI to buy AI startup from Jony Ive

Likely no coincidence that they announce their company, io, during Google I/O.

Search "io" on Google right now and see what comes up...

jinayon Giving Software Away for Free

That's not the only concern though. The web is by far the most accessible way to distribute something, which is paramount in getting people to use it.

jinayon Anthropic Economic Index: AI's Impact on Software Development

They really need to fix the kerning on some of their charts

jinayon Ask HN: Is it a good idea to make a tiny AI for fixing form input formats?

I wonder if you could use the Chrome local AI API to build something like this: https://developer.chrome.com/docs/ai

jinayon Show HN: Dia, an open-weights TTS model for generating realistic dialogue

For anyone who wants to listen, it's on this page: https://yummy-fir-7a4.notion.site/dia

jinayon Gemma 3 QAT Models: Bringing AI to Consumer GPUs

Make sure you're using the "-it-qat" suffixed models like "gemma3:27b-it-qat"

jinayon Google Is Winning on Every AI Front

Cursor is likely very tuned for Claude (prompts-wise and all) due to its dominance with 3.5 and now 3.7. Still, Gemini 2.5's tool calling has been pretty poor in my experience which Cursor heavily relies on.

jinayon Show HN: Windsurf – Agentic IDE

Fun fact: the Codeium office is actually the Pied Piper office from the show [1], so yeah, they like Silicon Valley.

[1] https://x.com/codeiumdev/status/1851400416946462967

jinayon Ask HN: What tools and practices have helped you work better as a developer?

How does it stack up against GitHub's own search?

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

Hmm, I've never used /. so it wasn't me who shared it.

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

Yep, it does some naive rescaling of the clock to make it circular (since perspective would make it more like an ellipse in the image), but then assumes 12 is always at the top.

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

Thanks!

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

Thank you!

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

Woah generalized pose estimation seems really useful and it's cool that the example is for reading a clock. Thanks for sharing!

jinayon Ask HN: What's the most creative 'useless' program you've ever written?

When I was first learning computer vision, I wrote a program that could tell the time from an image of a clock [1]. I had no purpose for it besides the fact that it seemed like a cool problem to try and solve.

Years later, I get an email from a stranger in Korea, asking me how to run my program. Why would he want to use my silly program? Turns out you can adapt the code to read analog pressure gauges which is really useful for chemical plants. Goes to show that there's often a use for most things.

[1] https://github.com/jinayjain/timekeeper

jinayon 90 Days – What I learned from quitting my job and going all-in

Thanks for taking the time to read! I tried to be brutally honest.

jinayon Cardinal – Virtual modular synthesizer plugin

I'm in the process of building a similar project aimed towards beginners, so it's hopefully a bit less daunting than Cardinal/VCV Rack.

https://wavepen.jinay.dev/

jinayon Ask HN: What are some "toy" projects you used to learn neural networks hands-on?

I built a simple autodifferentiation engine [1] in JavaScript when I was first learning about backpropagation. It's a great way to learn how frameworks like PyTorch work.

[1] https://blog.jinay.dev/posts/backprop/

jinayon Disengage your autopilot – a lesson from reinforcement learning

Did Shannon use it for something or just as an experiment?

jinayon Meta Llama 3

It's almost guaranteed that there will be quantizations and adaptations to consumer hardware that should make it both versions of the model accessible to mortals on consumer GPUs (and even CPUs).

jinayon Google Scholar PDF Reader

That seems really useful, thank you!