Hacker News: deevelton

Show HN: See when TV shows are ready to binge

deevelton — Wed, 07 Oct 2026 16:25:45 +0000

Made this for impatient people like me, who have trouble dealing with the torturous drip feed of one new TV series episode per week, and often search for "season finale air date" to determine when a show will finally be ready to binge.

Comments URL: https://news.ycombinator.com/item?id=49995028

Points: 5

# Comments: 1

New comment by deevelton in "Human in the Loop (A Short Story)"

deevelton — Wed, 09 Sep 2026 03:01:24 +0000

Thanks for reading it, I appreciate it!

Human in the Loop (A Short Story)

deevelton — Wed, 09 Sep 2026 01:42:54 +0000

Article URL: https://github.com/dvelton/human-in-the-loop

Comments URL: https://news.ycombinator.com/item?id=49619739

Points: 2

# Comments: 2

New comment by deevelton in "Ask HN: What are tools you have made for yourself since the advent of AI?"

deevelton — Tue, 09 Jun 2026 05:46:41 +0000

a tool that helps me work in hallucination-sensitive contexts

https://github.com/dvelton/eyeball

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Thu, 09 Apr 2026 14:50:19 +0000

one of my teammates experimenting with something along these lines :) https://github.com/jessephus/model-mosaic

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Thu, 09 Apr 2026 14:49:33 +0000

awesome! thanks for checking it out

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Wed, 08 Apr 2026 13:01:37 +0000

Not sure what happens if you start scaling this, but curious too. Would love to see someone who actually knows ML try it.

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Wed, 08 Apr 2026 12:52:49 +0000

Increased default epochs to 2000 instead of 500, I think that fixed it but let me know if you still run into this.

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Wed, 08 Apr 2026 06:41:07 +0000

Thanks; does this fix it? https://github.com/dvelton/ai-pixel/commit/ba04e1c649e0ec99b...

New comment by deevelton in "Show HN: Can an AI model fit on a single pixel?"

deevelton — Wed, 08 Apr 2026 03:00:30 +0000

This was just a fun thought experiment.

Feed it two inputs (e.g. chance of rain and wind speed; this is one of the examples in the demo) and it learns to answer a yes/no question like "bring an umbrella?" It's a one-neuron binary classifier with three learned parameters: two weights and a bias. Those three numbers map directly to Red, Green, and Blue. Save the model: you get a 1x1 PNG. Load the pixel: you get your classifier back. The color is the model.

Show HN: Can an AI model fit on a single pixel?

deevelton — Wed, 08 Apr 2026 00:32:56 +0000

Article URL: https://github.com/dvelton/ai-pixel

Comments URL: https://news.ycombinator.com/item?id=47683171

Points: 8

# Comments: 10

Show HN: A tool to make AI show evidence inline

deevelton — Sat, 04 Apr 2026 14:48:28 +0000

When working in hallucination-sensitive contexts (where cost of error is very high), found myself constantly jumping between AI outputs/analysis and source docs to see with my own eyes that a source doc says what the AI claims it says. This is a simple little tool that tries to alleviate that pain, based on the theory that screenshots are less likely to be hallucinated than text.

Comments URL: https://news.ycombinator.com/item?id=47639525

Points: 2

# Comments: 0

New comment by deevelton in "Do your own writing"

deevelton — Wed, 01 Apr 2026 00:13:51 +0000

I wonder if an animation with the prompts/edits inline and the text morphing might be an interesting UI…fun stuff to think about. Contributions welcome! https://github.com/dvelton/trace

New comment by deevelton in "Show HN: "Have your LLM talk to my LLM""

deevelton — Tue, 31 Mar 2026 13:30:46 +0000

This was just a small experiment, but as a teammate and I watched our respective agents (each loaded with its owner’s context/preferences/etc) negotiate directly with one another to schedule and agree on lunch plans on our behalf, there was definitely a feeling that what we were watching was the tip of an iceberg.

Show HN: "Have your LLM talk to my LLM"

deevelton — Tue, 31 Mar 2026 13:30:31 +0000

Article URL: https://github.com/dvelton/rendezvous

Comments URL: https://news.ycombinator.com/item?id=47587094

Points: 1

# Comments: 1

New comment by deevelton in "Show HN: A shot tracking app for hockey teams"

deevelton — Tue, 31 Mar 2026 03:59:28 +0000

Parents in my son's hockey league used to track shots on goal with pen and paper during games, to help coaches both during and after the games. It was tedious and the data was hard to use afterward.

Not a developer, so I used AI to build a free web app to replace it. You tap where on the rink each shot came from, tag whether it was a goal or save, and at the end of the game you get a full report with shot maps, heatmaps, and per-player breakdowns. Works on your phone, no account needed.

It's not fancy tech, but it's pretty rewarding to see it actually in use by the team and now even spreading to other teams in the league :)

Show HN: A shot tracking app for hockey teams

deevelton — Tue, 31 Mar 2026 03:56:41 +0000

Article URL: https://github.com/dvelton/hockey-shot-tracker

Comments URL: https://news.ycombinator.com/item?id=47582579

Points: 6

# Comments: 1

New comment by deevelton in "Do your own writing"

deevelton — Mon, 30 Mar 2026 21:13:33 +0000

was curious how it might look if we started seeing prompts/steering inline with the finished product: https://dvelton.github.io/trace/examples/the-post.html

New comment by deevelton in "A lawyer won Anthropic's hackathon – what everyone missed"

deevelton — Thu, 26 Mar 2026 13:58:30 +0000

Maybe it’s just personal deja vu, but in current discussions of vibecoding v software engineering I keep seeing parallels from the debates 20 years ago when blogs began proliferating: the bloggers v “real journalism” arguments.

New comment by deevelton in "Thinking Fast, Slow, and Artificial: How AI Is Reshaping Human Reasoning"

deevelton — Sat, 21 Mar 2026 21:58:59 +0000

Have been curious what it could look like (and whether it might be an interesting new type of “post” people make) if readers could see the human prompts and pivots and steering of the LLM inline within the final polished AI output.