HN user

eigenvalue

6,392 karma

Currently building pastel.network in NYC

See my open source projects here:

https://github.com/Dicklesworthstone

And my Twitter here: https://x.com/doodlestein

Posts153
Comments1,048
View on HN
github.com 14d ago

Show HN: FrankenMarkdown, Render .md Files to PDF/HTML (also in browser)

eigenvalue
2pts0
asupersync.com 4mo ago

Show HN: Asupersync, the Cancel-Correct Async Runtime for Rust

eigenvalue
3pts1
frankentui.com 5mo ago

Show HN: FrankenTUI in the Browser

eigenvalue
22pts10
frankentui.com 5mo ago

FrankenTUI Live Web Demo

eigenvalue
2pts2
www.youtube.com 5mo ago

Show HN: FrankenTUI

eigenvalue
4pts0
github.com 5mo ago

Show HN: Destructive_command_guard (Dcg)

eigenvalue
3pts0
phage-explorer.org 5mo ago

Show HN: Phage Explorer

eigenvalue
127pts35
brennerbot.org 6mo ago

Show HN: Brennerbot.org – Generalizing the scientific methods of Sydney Brenner

eigenvalue
3pts0
twitter.com 7mo ago

Show HN: Beads Viewer (Bv)

eigenvalue
1pts0
github.com 7mo ago

Show HN: Beads Viewer (Bv)

eigenvalue
4pts0
github.com 7mo ago

Show HN: Coding Agent Session Search (Cass)

eigenvalue
3pts1
twitter.com 8mo ago

When you're making tools for AI agents, ask them for their feedback

eigenvalue
1pts3
github.com 8mo ago

Show HN: EES, the Epstein Email Search System

eigenvalue
2pts0
twitter.com 8mo ago

Von Neumann Figured Out the Logic of How DNA Must Work Years Before Discovery

eigenvalue
11pts0
dicklesworthstone.github.io 8mo ago

Show HN: When 7 Codex Agents Sent Each Other 1k Messages over 2 Days

eigenvalue
1pts0
github.com 8mo ago

Show HN: Give your coding agents the ability to message each other

eigenvalue
14pts2
twitter.com 8mo ago

Coding Agents and Pachinko Parlors

eigenvalue
2pts0
twitter.com 8mo ago

When Coding Agents Can Send Each Other Messages, They Sound Human

eigenvalue
3pts0
github.com 8mo ago

Show HN: MCP Agent Mail, Like Gmail for Coding Agents

eigenvalue
4pts0
fixmydocuments.com 10mo ago

Factor Risk Models and the Hedge Fund Business

eigenvalue
2pts1
letter-learning-game.org 10mo ago

Show HN: Open-Source Game for Kids for Learning Letters and Phonics

eigenvalue
2pts0
dicklesworthstone.github.io 10mo ago

Show HN: Henry Kissinger's Undergraduate Thesis Website

eigenvalue
3pts0
twitter.com 11mo ago

AI-Powered Discoveries and the Camera Lucida

eigenvalue
2pts0
fixmydocuments.com 11mo ago

Making Complex Code Changes with Claude Code and Cursor

eigenvalue
1pts0
twitter.com 1y ago

Claude Code Agent Farm: Run Multiple Claude Code Sessions in Parallel

eigenvalue
2pts1
github.com 1y ago

Show HN: Claude Code Agent Farm

eigenvalue
4pts0
twitter.com 1y ago

OpenAI's o3 model is smart, but has a serious problem with lying

eigenvalue
2pts2
fixmydocuments.com 1y ago

Protecting Against AI Prompt Injection Attacks with Innoculation

eigenvalue
1pts0
github.com 1y ago

The Advanced Cognitive Inoculation Prompt (ACIP)

eigenvalue
2pts0
github.com 1y ago

Show HN: The Ultimate MCP Client

eigenvalue
7pts1
Goodbye to Sora 4 months ago

I posted this on X but it’s relevant here, so reposting it:

I had a lot of fun using Sora and got a lot of laughs with absurd videos of me in various situations.

But like everyone else, I kind of got it out of my system after a couple weeks. Not to mention that my family got sick of seeing them. And so my usage collapsed to zero. And that seems to have also been the pattern writ large.

But this kind of flash-in-the-pan dynamic is devastating for a product with this kind of profile, which requires insane amounts of compute hardware to serve while also having no short-term monetization path.

Meta could afford to invest in IG Reels even when it was burning money and costing them a fortune for hardware because it was building up what turned out to be sustainable usage patterns which persisted long after the initial spending ramp.

It’s basically impossible to effectively monetize anything that’s not sustainable on the order of multiple years.

A subscription-based model would see excessively high churn that would be ruinous to the economics, and also advertisers wouldn’t be interested either, for the obvious reasons.

So why couldn’t this work? I don’t think that it was because the models weren’t good enough or that the depictions weren’t realistic or lifelike enough. I still marvel at some of the better outputs I was able to get from Sora.

I think the fundamental problem that Sora faced is actually much broader and more general, and it comes down to the basic Pareto math of any content generation or creative app, which is that 95%+ of the users just want to passively consume content from the 5% or less that actually wants to generate it (and is capable of making anything that other people want to watch).

It was really dismal to see the repetitive, trite ideas that 99% of users generated in the public feed. Just the same few dumb jokes and things they copied from other users.

Or putting themselves in a scene with their favorite fictional or cartoon characters or whatever, which of course got banned pretty quickly for copyright issues.

Most people are not creative and don’t have a lot of original, interesting ideas. So that means that the vast majority of the content is always going to come from a vanishingly small number of creators in a power law distribution.

And those super-creators aren’t going to want to be limited to a simple text-based interface that can only generate for 10 seconds at a time with no continuity and where large portions of things you might want to try are strictly forbidden.

They’ll instead gravitate to more customized solutions for power users that regular users would find as overwhelming to use as AutoCAD.

And that’s what you’re seeing now with all the new viral AI slop videos that are made by a handful of creators who have figured out the workflows and are pumping out the worst junk you can imagine that gets people to click and watch.

Anyway, RIP Sora; it was fun while it lasted. Thanks, Sam, for blowing a few hundred million bucks so we could get some laughs.

I find this to be a bizarre sentiment. It’s an artifact that exists. The chances of me making this by hand are 0. This would be a full time job for 3 years to research and build this. For 10 people. And it would have to charge a ton of money to access in that case.

I really think git worktrees are a bad approach. You’re better off in my view with one shared state and dealing with conflicts live by dividing tasks ahead of time using beads and letting agents communicate with each other using Agent Mail and file reservations.

I’ve been able to productively run 12+ agents from CC, Codex, Gemini-cli at the same time this way and it works really well.

I was recently explaining to someone how Barra risk factor models work and how they’re used by hedge funds to measure whether someone actually has investing skill or just “got lucky” (among many other use cases). And I realized that it would make an interesting article. So enjoy!

They need to come up with a better way of detecting people who are actively breaking the ToS by using the Max plans as a kind of backdoor API key, because those users are obviously not using it in the way it was intended and abusing the system. Not sure how they would do that, but I'm guessing you could fingerprint the pattern of requests and see that some of the requests don't fit the expected pattern of genuine requests made by the Claude Code client.

Anyway, I've been resigned to this for a while now (see https://x.com/doodlestein/status/1949519979629469930 ) and ready to pay more to support my usage. It was really nice while it lasted. Hopefully, it's not 5x or 10x more.

My favorite of these programmer fonts is PragmataPro, which I bought around 5 years ago. I like how it’s denser while still being easy to read.

Only problem is that it doesn’t have all the nerd font glyphs so it can’t handle the nice oh-my-zsh themes well, like the powerline-10k theme. I still use it despite that though.

A new PNG spec 1 year ago

You’re doing god’s work here, thanks for your service! I use photopea all the time. Probably the most impressive web app I’ve seen in terms of performance.

LLMs really know how to use it incredibly well. You can ask them to do just about any video related task and they can give you an ffmpeg one liner to do it.

I’ve made tons of improvements to this just in the past day. I thinks it’s already the most feature packed and nice looking MCP client out there now.