Viewing profile — rush86999
rush86999
HN member- Joined
- Fri, Jan 26, 2018, 3:17 AM UTC
- HN karma
- 32
- Public activity
- 76 items
- HN profile
- View on Hacker News ↗
About rush86999
No profile information was provided.
Recent public activity
-
comment
Comment #49186507
That's what he was trying to imply
-
comment
Comment #49148457
It's opus 5 > Kimi K3 > grok 4.5 That's a pretty good benchmark
-
comment
Comment #49127865
I'm still working on mine: https://github.com/rush86999/atom/blob/main/docs/architectur...
-
comment
Comment #49103240
How is this different from OpenRouter? I also developed something similar for my agent harness. It's based on model predictors and an exponential moving average: https://github.com…
-
comment
Comment #49059292
AI is only replacing low-level work. It will eventually move on to high-level work. One missing point: careers that require communication, especially person-to-person, won't be rep…
-
comment
Comment #49059243
The main goal is AGI, and the underlying prerequisite theme is continuous learning. Everyone is trying to figure out how to achieve this prerequisite. I'm thinking of agent harness…
-
comment
Comment #48986619
Same here! https://github.com/rush86999/atom
-
comment
Comment #48904658
Autonomous Task Orchestration Management Agent === ATOM Agent
-
comment
Comment #48901289
Firecracker microVMs are safest. That's what I added to my repo; see above.
-
comment
Comment #48900176
Is this manipulating excel files using agent AI? How is this different from using a python package like openpyxl and adding a UI layer on top with agentic co-editing? https://githu…
-
comment
Comment #48900063
OpenClaw needs to be built from the ground up. I created Atom based on current research on agentic systems and am looking for maintainers & testers to help out. https://github.com/…
-
comment
Comment #48866831
China has a huge microwave to destroy any kind of Starlink over its head.
- story
- story
-
comment
Comment #48539275
Working on: https://www.novopathmedical.com/ - evidence-based guidance of diet, exercise, and mental health via SMS for end users. Clinician-guided feedback to bots. https://github…
-
comment
Comment #48404976
Just as you expected, I'm throwing in my harness. Please support: https://github.com/rush86999/atom
-
comment
Comment #48159027
You would think git history should be the first thing an agent would look at, as they make so many mistakes before they get to the correct answer. They don't. I haven't measured, b…
-
comment
Comment #47238597
Nope - just use memory layer with model routing system. https://github.com/rush86999/atom/blob/main/docs/EPISODIC_ME...
-
comment
Comment #47237447
Only solution is to train the issue for the next time. Architecturally focusing on Episodic memory with feedback system. This training is retrieved next time when something similar…
-
comment
Comment #47224337
Everyone is using OpenClaw for personal productivity, but you're right. Not much value, as you can get that from existing products. The market will eventually realize the business …
-
story
Show HN: Atom – open-source AI agent with "visual" episodic memory
Hey HN, I’ve been building Atom ( https://github.com/rush86999/atom ), an open-source, self-hosted AI automation platform. I built this because while tools like OpenClaw are excell…
-
comment
Comment #47173225
This is an incomplete thought. A strong checks and balances without influence of bias, relationships, and politics can be implemented using a 2-way blind system where: 1. decision …
-
comment
Comment #47090826
Funny you described everything I worked on for this project: https://github.com/rush86999/atom Cats out of the bag. Everyone knows the issue and I bet a lot of people are trying to…
-
comment
Comment #47076485
I would create a custom component that integrates into your IDE or create a plugin and add AI accessibility via logs. I 'm doing something similar to my current app that I'm buildi…
-
story
Show HN: Atom – Safer Version of OpenClaw with Episodic Memory
Atom is what you would want if you wanted OpenClaw to run your business. Here are the key differences: - Governance and audit trails - You want graduated autonomy (agents earn trus…