Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What Are You Working On? (March 2026)

news.ycombinator.com

Post reply on HN
Print view View original

101–110 of 1001 posts

Re: Ask HN: What Are You Working On? (March 2026)

#101

Post by Mockapapella »

I'm working on a TUI-based agent orchestrator called Tenex: https://github.com/Mockapapella/tenex

It's gone a long way to solve the "review" bottleneck people have been experiencing (though admittedly it doesn't fix all of it), and I'm in the process of adding support for Mac and Windows (WSL for now, native some other time).

Some of the features I've had for a while, like multi-project agent worktrees, have been added as a part of the Codex App, so it's good to see that this practice is proliferating because it makes it so much easier to manage the clusterf** that is managing 20+ agents at once without it.

I'm feeling the itch to have this working on mobile as well so I might prioritize that, and I'm planning to have a meta-agent that can talk to Tenex over some kind of API via tool calls so you can say things like "In project 2, spawn 5 agents, 2 codex, 2 claude, 1 kimi, use 5.2 and 5.4 for codex, use Opus for the claudes, and once kimi is finished launch 10 review agents on its code".

Re: Ask HN: What Are You Working On? (March 2026)

#102

Post by arthurcolle »

dataviz1000 wrote: post #41

I'm using TimescaleDB to manage 450GB of stocks and options data from Massive (what used to be polygon.io), and I've been getting LLM agents to iterate over academic research to see if anything works to improve trading with backtesting. It's an addictive slot machine where I pull the lever and the dials spin as I hope for the sound of a jackpot. 999 out of 1000 winning models do so because of look-ahead bias, which m…

did RH open up API for trading?

Re: Ask HN: What Are You Working On? (March 2026)

#103

Post by happiness0067 »

dataviz1000 wrote: post #41

I'm using TimescaleDB to manage 450GB of stocks and options data from Massive (what used to be polygon.io), and I've been getting LLM agents to iterate over academic research to see if anything works to improve trading with backtesting. It's an addictive slot machine where I pull the lever and the dials spin as I hope for the sound of a jackpot. 999 out of 1000 winning models do so because of look-ahead bias, which m…

Relateable. If I had a dollar for every time I ran into issues with time zones, that would be a profitable strategy in and of itself.

Re: Ask HN: What Are You Working On? (March 2026)

#104

Post by tgrowazay »

dataviz1000 wrote: post #41

I'm using TimescaleDB to manage 450GB of stocks and options data from Massive (what used to be polygon.io), and I've been getting LLM agents to iterate over academic research to see if anything works to improve trading with backtesting. It's an addictive slot machine where I pull the lever and the dials spin as I hope for the sound of a jackpot. 999 out of 1000 winning models do so because of look-ahead bias, which m…

I tried exactly this - loading polygon.io data into TimescaleDB, and it was very inefficient.

Ended up using ClickHouse - much smaller on disk, and much faster on all metrics.

Re: Ask HN: What Are You Working On? (March 2026)

#105

Post by movedx »

I've written and I'm now polishing and refining a tool for on-set data management for small to medium scale productions. I do Data Wrangling on the side and one of the hardest things to do is keep track of drives, backup jobs, and link them all together whilst knowing where everything is stored, who has what, how much data you have left, how much data you're going to use on the next scene given it's filmed on camera X using Y settings, and so on.

It's written in Golang and acts as a simple desktop app that creates a web server and then opens the site in your default browser. This way it's easily multi-platform and can also be hosted as a SaaS for larger production houses.

Re: Ask HN: What Are You Working On? (March 2026)

#106

Post by happiness0067 »

djb_hackernews wrote: post #28

I live in an old house. The front bump out leaks when we get driving rain. I installed some flashing but that wasn't enough, it's still leaking. So I'm working on that so I can close up the big hole in the ceiling some day. The prior owners filled in the old coal chute with literal bags of cement sort of artistically placed in the hole in the brick foundation. So I'm trying to figure out what masonry tools and skills…

As in they put bags of unmixed cement in the chute?

Very exciting on the playhouse. What kind of things will it have?

I'm expecting my first this year so have a ways to go before I get to work on that project

Re: Ask HN: What Are You Working On? (March 2026)

#107

Post by mmaunder »

dataviz1000 wrote: post #41

I'm using TimescaleDB to manage 450GB of stocks and options data from Massive (what used to be polygon.io), and I've been getting LLM agents to iterate over academic research to see if anything works to improve trading with backtesting. It's an addictive slot machine where I pull the lever and the dials spin as I hope for the sound of a jackpot. 999 out of 1000 winning models do so because of look-ahead bias, which m…

Nice. I played with this a bit. Agents are very good at Rust and CUDA so massive parallelization of compute for things like options chains may give you an edge. Also, you may find you have a hard time getting very low latency connection - one that is low enough in ms so that when you factor in the other delays, you still have an edge. So one approach might be to acknowledge that as a hobbyist you can't compete on lowest-latency, so you try to compete on two other fronts: Most effective algorithm, and ability to massively parallelize on consumer GPU what would take others longer to calculate.

Best of luck. Super fun!

PS: Just a follow-up. There was a post here a few days ago about a research breakthrough where they literally just had the agent iterate on a single planning doc over and over. I think pushing chain of thought for SOTA foundational models is fertile ground. That may lead to an algorithmic breakthrough if you start with some solid academic research.

Re: Ask HN: What Are You Working On? (March 2026)

#108

Post by lpellis »

suresh70 wrote: post #96

I am working on a SSL certificate monitor. It comes with its own probe that can scan your private infra and collect the certs for monitoring. It also has a web interface for monitoring SSL certificate of any public domain. There are a few chinks here and there. Hope I can get it over by this month. https://www.certgorilla.com

Ironically I'm getting SSL handshake failed on your site

Re: Ask HN: What Are You Working On? (March 2026)

#109

Post by Aeolun »

YesBox wrote: post #59

I changed gears and moved into the video games industry at the end of 2021. I started developing a city builder called Metropolis 1998 [1], but wanted to take the genre in new directions, building on top of what modern games have to offer: - Watch what's happening inside buildings and design your own (optional) - Change demand to a per-business level - Bring the pixel art 3D render aesthetic back from the dead (e.g R…

Cool! Isometric for the win :)

Re: Ask HN: What Are You Working On? (March 2026)

#110

Post by mbreese »

pipnonsense wrote: post #72

A soccer web game where you are the coach and your only possible interaction is shouting (ie typing) messages to your players from the sidelines. An LLM interpret your messages and pass instructions into the game engine. It is a pretty fun project

I could see this being a very eye opening game if you added "Fan" and "Parent" modes. In "fan" mode nothing you said would affect the game, although maybe a player would laugh once in a while. In "parent" mode, you'd have a youth soccer game where whatever you said would confuse the player and they'd perform worse.

Sounds like a fun project -- like a more interactive version of Football Manager.

Post reply on HN