Ask HN: What Are You Working On? (June 2025)

Neat! I sometimes play around with the idea of reverse engineering and transcompiling a tiny game that I think was probably written in Turbo Pascal 4.0. Maybe 4.0 supported optimizations, but this program seems to have been compiled in a debug mode. (At least, it seems to have no optimization, and has the default {$S+} stack overflow checking at the start of every function.) The lack of optimization makes it (and perhaps other programs written in Turbo Pascal) a really attractive artifact to experiment with transcompiling. When I realized that only the first segment was the actual game, and the other three segments corresponded to standard units used for I/O (etc.), which could be harder to analyze, I realized I could just omit those segments and replace them with new functions suitable for the transcompilation target. Maybe some day I'll get around to finishing it.

Good luck!

I've been learning how to make server-side mods for my Minecraft server: https://swedenmayhem.se/minecraft/

The goal is to make a Minecraft server that constantly updates itself, giving you "unlimited content", while still retaining any progress you've made so far.

I've been working on semantic search for Mac for the last few weeks.

It's called SmartSearch - uses SentenceTransformers for embeddings and FAISS for fast similarity search. Best of all, it runs locally on your computer.

Why? I absolutely despise Mac's search. I want to be able to search within documents, images, pdf etc.

Github: https://github.com/neberej/smart-search/

Demo: https://github.com/user-attachments/assets/aed054e0-a91f-459...

Mostly writing for myself; I should really convert some drafts into proper blog posts because I'm really interested in discussing my ideas with others.

I've been thinking a lot about the current field of AI research and wondering if we're asking the right questions? I've watched some videos from Yann LeCun where he highlights some of the key limitations of current approaches, but I haven't seen anyone discussing or specifying all major key pieces that are believed to be currently missing. In general I feel like there's tons of events and presentations about AI-related topics but the questions are disappointingly shallow / entry-level. So you have all these major key figures repeating the same basic talking points over and over to different audiences. Where is the deeper content? Are all the interesting conversations just happening behind closed doors inside of companies and research centers?

Recently I was watching a presentation from John Carmack where he talks about what Keen is up to, but I was a bit frustrated with where he finished. One of the key insights he mentions is that we need to be training models in real-time environments that operate independently from the agent, and the agent needs to be able to adapt. It seems like some of the work that he's doing is operating at too low of an abstraction level or that it's missing some key component for the model to reflect on what it's doing, but then there's no exploration of what that thing might be. Although maybe a presentation is the wrong place for this kind of question.

I keep thinking that we're formulating a lot of incoherent questions or failing to clearly state what key questions we are looking to answer, across multiple domains and socially.

Looks great, and smart differentiation!