Ask HN: What are you working on? (May 2026)

[flagged]

I've been building this "general problem solver" (will likely focus on math problems first) that uses a special kind of orchestrator to direct/structure the problem solving approach in accordance with how many 'rounds' remain and other aspects of problem context. It does this largely by influencing the behavior of specialists.

Just posted a first early demo and sample orchestrator system prompt yesterday: https://x.com/Westoncb/status/2053429329233895857

You initialize the system with an objective and a number of rounds to run for, and it loads the current config (orchestrator + specialist prompts and LLM configs) and begins working on it. You can manually step one round at a time or just let it run.

Rather than accumulating a single long work log/context, at each round specialists apply patches to a number of named 'artifacts' with different roles (e.g. uncertainties, dead ends, findings), which are injected into prompts during subsequent rounds.

The engine is written in rust and there's a web UI (and CLI). You can use the built in config editor to define specialists (and their prompts), what the artifact set is, orchestrator prompting etc.

I've just published my first book. The central argument is simple: software development is a design activity, not a construction activity — and confusing the two is the root cause of most project failures. Written for developers, managers, and anyone who has ever wondered why building software is so much harder than it looks.

It's on Amazon in both Kindle and paperback formats.

https://www.amazon.com.au/Code-Design-software-projects-deve...

I’ve been building an uptime monitor service for a while now, something that is genuinely reliable and only alerts you when something is actually going on. Also comes with very pretty status pages!

Free tier is enough for most users, paid tier just exists to gate the stuff that is expensive to run like SMS alerts.

Check it out at [Larm](https://larm.dev) and try out the [response time checker too](https://larm.dev/tools/response-time) to try out the Larm probe infrastructure.

I've been using https://github.com/gchamon/buzz as an opportunity to have a WebDAV with tight integration with real debrid, jellyfin and opensubtitles. It solves the requirement of jellyfin for having a single file per folder even if the original source had many files in them, adds confirmation for removing entries from debris, has an archive so deletions can be restored, a simple but powerful integration with opensubtitles and a functional logs UI. It's also an opportunity for me to review web design concepts and experiment heavily with coding agents, both local and SOTA.