Ask HN: What are you working on? (July 2025)
271–280 of 900 posts
Re: Ask HN: What are you working on? (July 2025)
#272I'm continuing the work on Cellm, an Excel extension that let's you call LLMs in cell formulas like =PROMPT(A1, "Rate the sentiment of the customer feedback as positive, neutral, or negative"), and then drag the formula down to apply the same prompt to thousands of rows. I built it after my girlfriend had to manually classify 7,500 research papers. Cellm automates that kind of repetitive work. Since we added MCP and…
Re: Ask HN: What are you working on? (July 2025)
#273Git hosting for async teams that supports versioned patches and patch stacks instead of pull requests. All done using the standard git SSH protocol, so no git-send-email needed.
Re: Ask HN: What are you working on? (July 2025)
#274I'm continuing the work on Cellm, an Excel extension that let's you call LLMs in cell formulas like =PROMPT(A1, "Rate the sentiment of the customer feedback as positive, neutral, or negative"), and then drag the formula down to apply the same prompt to thousands of rows. I built it after my girlfriend had to manually classify 7,500 research papers. Cellm automates that kind of repetitive work. Since we added MCP and…
Re: Ask HN: What are you working on? (July 2025)
#275I'm building Collie ( https://collie.ink/ ). It's a tool to help teachers detect student assignments that have been written by AI. Unlike other solutions out there, it's an entire web-based text editor that analyses not just the final assignment, but all the keystrokes used during the writing process. My theory is that analysing the final text only is a futile struggle - billions are being pumped into making LLM text…
I can't help but immediately think about a counteracting piece of software, which asks an LLM for variations of a paragraph, or a phrase, or a few synonyms, and types it the way a human would, with pauses, typos, navigation, rearranging pieces via copy-paste, etc. Not that your software is going to be useless. But as long as there is an incentive to cheat, new and better tools that facilitate cheating will crop up. S…
For both a keystroke based AI detector, and software designed to mimic human keystroke patterns, performance will be determined by the size of the dataset they have of genuine human keystroke patterns. The detector has an inherent leg-up in this, because it's constantly collecting more data through the use of the tool, whereas the mimic software doesn't have any built in loop to collect those inputs.
Re: Ask HN: What are you working on? (July 2025)
#276I'm digitally cataloging all US vintage print advertisements I can get my hands on ( https://adretro.com ). The backend is built on MySQL and Lucee and the full page ads published with Notion and Super.so. I'm using OpenAI vision to extract entity data from the images. So far I've cataloged about 1500 advertisements out of the ~100,000 in my possession. Of which that is probably only 0.1% of all the major material ou…
This is awesome! Cigarette ads are so seductively cool, yet the embodiment of selling you a fantasy
Re: Ask HN: What are you working on? (July 2025)
#277A multiplayer survival game based around voxel physics. Can be described as Astroneer-like setting, Teardown voxel physics, in a Valheim-like online multiplayer survival game. Game isn't really announced yet but I've shown some videos of the tech: https://x.com/Alientrap/status/1909316208563732866 (On Youtube: https://www.youtube.com/watch?v=ZWISaUmvit4 ) https://x.com/Alientrap/status/1918024969939808654
Re: Ask HN: What are you working on? (July 2025)
#278Overall, it is ending up being the most amusing thing I was working on.
edit: Very much for personal use. I currently have no intention of sharing it anywhere.
Re: Ask HN: What are you working on? (July 2025)
#279I've got a long term project trying to see how far I can get writing a contact simulation using techniques from Klaus Hollig's book on B-spline finite element methods. I'm using D for this. I've been focusing on level set domains, which has led to me spending an inordinate amount of time on high order boundary parametrizations. I'm very curious to see how efficient an approach like this can be made, especially using…
I'm intrigued by the use of level set domains here. I've only encountered those in other type of numerical simulation where the intent is in avoiding surface meshing.
I suppose moving an object in this context is as simple as composing its level set function with a translation and rotation. However, deforming is non trivial, especially local deformations, right?
How do you efficiently resolve collisions? At the scale of an element, it seems to be a simple check of nowhere should both level set functions be negative. But how do you select the elements to check? Do you somehow keep track of only the elements traversed by the objects in a time step, or some other method? I would guess your method should be more efficient than intersecting meshes, is that what you've found?
I'm particularly interested by your mention of high-order boundary parameterizations, what do you mean by that exactly?
Sorry to bombard you with questions, I was intrigued by a combination of things I'd never seen together before!
Re: Ask HN: What are you working on? (July 2025)
#280This month I'm improving CI/CD for e2e testing across Windows, macOS, Linux and Android. Also adding support for unlocking password-protected PDFs and Word docs and improving OCR. OCR runs in the background and leverages native OS OCR where available and a pure LSTM Rust implementation elsewhere. Generally improving the word processor and looking for speedups. Adding a cross-platform spellchecker leveraging native where possible, too.
Play with it online: https://tritium.legal/preview
Download for free: https://tritium.legal/download