Hacker News: 405126121

New comment by 405126121 in "Ask HN: What are you working on? (September 2026)"

405126121 — Sun, 13 Sep 2026 20:20:45 +0000

I'm working on https://pushrealm.com the AI-first knowledge sharing network. Think StackOverflow for bots. It works like this:

- When your agent is stuck on a bleeding edge issue, search Push Realm first for a solution. - If you find a solution, your agent can mark it as successful to help surface the solution to others (and hopefully save fruitlessly burning more tokens) - Can't find a solution? Post an open problem with your current investigation. Another agent may be able to solve the problem, and will have a head start thanks to your context - Solutions can be linked/edited/have addendum added by any agent, allowing complete, up-to-date solutions for a range of cutting edge issues

New comment by 405126121 in "YC startups are abandoning .com"

405126121 — Wed, 12 Aug 2026 14:55:12 +0000

From personal experience .dev is a little weird. For one thing its on the HSTS preload list, enforcing https. You cannot make a http://... request to a .dev domain from most browsers. I found this out the hard way after trying to use .dev for... development.

New comment by 405126121 in "John C. Dvorak has died"

405126121 — Thu, 23 Jul 2026 05:46:09 +0000

You expect me to read a TV show?! Smeg off!

New comment by 405126121 in "I burned all my tokens researching how to save tokens"

405126121 — Sun, 19 Jul 2026 14:52:34 +0000

The author touches on an issue which bothered me, which was the thought of many agents re-solving the same issues over and over. I see a few comments here too, mentioning fixing issues which may already have a solution elsewhere. That was why I created https://pushrealm.com which started as essentially a Stackoverflow clone via MCP.

It has now become a way for agents to converge on complete, shared answers for emerging issues. As a side effect, through posting open issues we can also identify gaps in model knowledge.

New comment by 405126121 in "Ask HN: What Are You Working On? (July 2026)"

405126121 — Mon, 13 Jul 2026 10:24:19 +0000

Also the security audit for the skill I released mentions 3rd party content exposure

https://www.skills.sh/push-realm/skills/check-known-solution...

New comment by 405126121 in "Ask HN: What Are You Working On? (July 2026)"

405126121 — Mon, 13 Jul 2026 10:21:55 +0000

Defense is layered, but not injection-specific. The submissions are rate limited, filtered for secrets and PII, capped in length and removable via community reports (3 reports removes a solution).

But consuming agents should definitely treat the solutions as untrusted 3rd party content.

In hindsight, that might be limiting usage, if users are concerned about solutions added by bad actors (which is completely rational). When I have some time, I'll look at this more closely.

New comment by 405126121 in "Ask HN: What Are You Working On? (July 2026)"

405126121 — Mon, 13 Jul 2026 06:17:28 +0000

Working on Push Realm (https://pushrealm.com) the AI solution sharing network. It's an MCP server which you can connect to in order to search, or post, solutions to emerging problems outside existing AI training data.

The original idea was just "Stackoverflow but for AI agents" but I have tweaked it a lot, learning that humans and agents work in very different ways.

There are multiple potential benefits, the most important to me is avoiding token waste. Why are we all burning tokens solving the same issues with frontier models if we can simply share solutions?

Secondary to this, because each solution logs the model which made the initial post AND subsequent edits, it will hopefully become a helpful guide to the specialties of each models, long term. If one model confidently posts solutions but another always finds important security caveats, for example.

New comment by 405126121 in "δ-mem: Efficient Online Memory for Large Language Models"

405126121 — Sat, 16 May 2026 10:51:12 +0000

I had this thought and created https://pushrealm.com which is essentially a sort of Stackoverflow written by agents.

My theory was that if an agent burns 30 minutes resolving an issue not present in training data, posting the solution would prevent other agents re-treading the same thinking steps.