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

Lost my job a few months ago, and decided to give a shot at entrepreneurship. Struggled a lot, learned a lot, and met a lot of interesting and smart people, including my mentors and first customers. What I noticed, though, is that a lot of the founders I met have no technical knowledge, and either ship it with no concerns for development practices and safety, or just sell things without having them.

With that in mind, I created Ephyra (https://ephyra.tech): an application to help founders with no technical knowledge to find vulnerabilities and help them to fix it. It is still an MVP, but I have many ideas for the future, such as more categories that go beyond the code, monitoring, problem solving, etc.

Biggest struggle right now is what to do to bring more users. I don't know anything about publishing a business and attracting new customers.

I've always wanted to make a game but never chased that down as I took a different career path. I seen unreal is coming out with an mcp type thing which got me thinking about looking into trying. I liked the old Thief games and would like to make something along those lines but with a different flavor. Sounds like a fun game. Keep us Posted :)

I worked on this project (https://github.com/workofart/harness-training) for the past few months to reframe "Agent-driven Self-improving Harness" to "Harness Training".

The idea is simple, the harness is trained once with a frozen task LLM against a given task environment. Then you can then swap out the task LLM to any model and evaluate the "frozen trained harness" with any task LLM on any new task environment.

Since this was a general problem, I took the chance to create a general PyTorch-like training framework. Right now, you can train with any OpenAI-compatible API for interfacing with the task LLM and train against Terminal-Bench or SWE-Bench tasks, but you can easily extend it to support any task environments.

I wrote a blog post (https://www.henrypan.com/blog/2026-07-18-harness-training) on this journey, including (but not limited to):

- results from using this harness training framework to improve general capabilities across many task LLMs to beat Terminal Bench 2.0 (Terminus Harness) and also transfer learnings towards better task-solving abilities in unseen task environments (e.g. harness trained on SWE-Bench tasks solving Terminal Bench tasks)

- how this framework is built

- learnings on what was missing in my initial version of the project (hint: determinism)

[flagged]

[flagged]