Viewing profile — suninsight
suninsight
HN member- Joined
- Fri, Jun 07, 2024, 7:49 AM UTC
- HN karma
- 22
- Public activity
- 46 items
- HN profile
- View on Hacker News ↗
About suninsight
Recent public activity
-
comment
Comment #46776414
[dead]
-
comment
Comment #46501056
[dead]
- story
-
comment
Comment #46120485
[dead]
-
comment
Comment #45800917
[dead]
-
comment
Comment #45738774
[dead]
-
comment
Comment #45388023
[dead]
-
comment
Comment #45387992
[flagged]
-
comment
Comment #45383001
Very cool and nicely executed ! Definitely see a lot of value in this. I was actually building a version of this using NonBioS.ai, but this is already pretty well done, so will jus…
-
comment
Comment #45361297
So I can attest to the fact that all of the things proposed in this article actually works. And you can try it out yourself on any arbitrary code base within few minutes. This is h…
- story
-
comment
Comment #44866369
how about halarax ...halucinate and paralax
-
comment
Comment #44865441
So we tried that route - but problem is that these interfaces aren't suited for asynchronous updates. Like if the agent is working for the next hour or so - how do you communicate …
-
comment
Comment #44864989
I think if you use Cursor, using Claude Code is a huge upgrade. The problem is that Cursor was a huge upgrade from the IDE, so we are still getting used to it. The company I work f…
- comment
-
comment
Comment #44518102
1. Multi-Agent is divide a part into tasks and hand off each part to a different Agent. This is different in the sense that a task is not divided into parts aprior. When the agent …
-
comment
Comment #44510002
He is NOT talking about multi-agent systems, which is exactly why he is calling it an Agency. The author goes to great length to explain why this is NOT a multi-agent system becaus…
-
comment
Comment #44509985
This isn't multi-agents at all. Infact if you read the article in detail, you will realize that the author goes in detail to explain how this system is different from multi-agents.…
- story
-
comment
Comment #44456678
So what we do at NonBioS.ai is to use a cheaper model to do routine tasks, but switch to a higher thinking model seamlessly if the agent get stuck. Its most cost efficient, and we …
-
comment
Comment #44367199
This will not end well.
-
comment
Comment #44317940
Most of our stuff is built in house actually, simply because everything else is still kind of catching up. You can find a bunch of information on the blog ( https://www.nonbios.ai/…
-
comment
Comment #44317906
It is AI Software Dev called NonBioS.ai
-
comment
Comment #44307742
As someone who works for a company having a real Agent in production, (not a workflow), I cannot disagree more than the very first statement here: Use Agent Frameworks like Langrap…
-
comment
Comment #44003611
Yes, but we dont believe that this is a 'fundamental' problem. We have learnt to guide their actions a lot better and they go down the rabbit a lot less now than when we started ou…