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

I'm bootstrapping and covering LLM costs for Ward's first couple hundred users (got about 50 users at the moment) to improve it. We have a local mode for added privacy and are dipping our feet to gauge biz. interest (client-side phishing protection is unparalleled).

I've recommended it to friends, colleagues and loved ones. I dogfood my own product, and it even surprises me every day how much more mindful it makes me of my browsing of harmful content. Would love to get feedback and testers from HN.

On the Chrome Web Store -> https://tryward.app

Still WIP but we are getting our first audit in the coming days!

Stoffel-Lang:https://github.com/Stoffel-Labs/Stoffel-Lang StoffelVM: https://github.com/Stoffel-Labs/StoffelVM MPC protocols: github.com/Stoffel-Labs/mpc-protocols Website: stoffelmpc.com

https://stonetools.ghost.io

Previous articles which resonated with HN were on Deluxe Paint and VisiCalc. The latest post, "HyperCard on the Macintosh," seems to be making the HN rounds currently. Bret Victor himself chimed in on the HyperCard article over on Mastodon, filling in some nice historical footnotes. https://posts.dynamic.land/@bret/115716576717006637

Unlike many (most?) other retrocomputing explorations, I specifically do not look at games nor do I tie myself to any particular machine, though I'm focused on the 1977 - 1995 period. I spend a minimum of two weeks with each productivity title, trying to learn it, building things with it, and generally trying to understand its approach to solving problems. I'd characterize my writing tone as casual, conversational, and decidedly light-hearted.

Each piece of software (so far, knock on wood) gets me thinking about some other aspect of related computing history, so I explore that as a tangent. With the Superbase article, I talked about "the paperless office." With the VisiCalc article I considered its impact on less obvious industries, notably hog farming.

I hope the passion and effort I put into the articles comes through. If you're interested in computing history beyond just the games I think you'll find something of interest on my blog. "This Week in Retro" did a segment about me and my various projects as well, if you're curious to get an overview of what I'm all about (link is queued up at the start of the segment) https://youtu.be/UHYscl1Ayqg?si=7JM1sZagjoqvPjk2&t=2137

Minemizer is a data formatter that produces csv-like output, but supports nested and sparse data, is human readable and super simple.

It produces even less tokens than csv for flat data, due to most tokenizers better tokenizing full words that contain a space before the word, and leads to less fragmentation.

There are many cool things I discovered while running tons of testing and benchmarking, but it's getting late here.

Code, benchmarks, tokenization examples and everything else can be found in the repo, but it is still very WIP: https://github.com/ashirviskas/minemizer

Or here: https://ashirviskas.github.io

EDIT: Ignore latency timings and token counts in "LLM Accuracy Summary" in benchmarks as different size datasets were used to generate accuacy numbers while I was running tons of experiments. For accurate compression numbers see compression benchmarks results. Or each benchmark one by one.

I will eventually fix all the benchmark numbers to be representative.