HackerTrans
トップ新着トレンドコメント過去質問紹介求人

vishnukool

no profile record

投稿

[untitled]

1 ポイント·投稿者 vishnukool·12 日前·0 コメント

[untitled]

1 ポイント·投稿者 vishnukool·25 日前·0 コメント

Ask HN: Are all the YC founders lying offlate?

3 ポイント·投稿者 vishnukool·2 か月前·0 コメント

Show HN: Open source setup to self-host OpenClaw instances on any host

github.com
7 ポイント·投稿者 vishnukool·5 か月前·9 コメント

[untitled]

1 ポイント·投稿者 vishnukool·5 か月前·0 コメント

[untitled]

13 ポイント·投稿者 vishnukool·5 か月前·0 コメント

Show HN: YC Advisor – AI grounded in 434 YC essays, interviews, and lectures

agent37.com
2 ポイント·投稿者 vishnukool·6 か月前·0 コメント

Show HN: Agent37 – Monetize your Claude skills with shareable links

agent37.com
5 ポイント·投稿者 vishnukool·6 か月前·3 コメント

コメント

vishnukool
·2 か月前·議論
The problem is that LLMs do not have a conceptual grounding in actual time. They estimate based on statistical correlation found in their training data which is filled with standard corporate project management timelines legacy codebases and waterfall estimates.
vishnukool
·2 か月前·議論
Good one. One thing that's becoming clear is that agent security is less about jail break prompts and more about permission boundries, hidden context flow and un intended tol behavior.
vishnukool
·2 か月前·議論
System design definitely carries more weight now but Leetcode has not totally vanished. It's just evolved.
vishnukool
·2 か月前·議論
Respect. It's a good day to remember the impact they had even if they are no longer around to pick up the phone. Btw calling her now.
vishnukool
·2 か月前·議論
This is the weird part of AI hallucinations and people start treating it like a verified fact after it gets repeated.
vishnukool
·5 か月前·議論
What have you seen to be the bottleneck ?

From the usage patterns I've seen for 90% of the use cases it seems to be fine, the one exception being Browser based use cases which chugs memory and so needs a beefier machine.
vishnukool
·5 か月前·議論
Very true and actually totally spot on!

It's the damn chromium instances that chugs memory like an Irish man chugs beer. I experimented launching containers with it and quickly realized the tiny shared infra hosts are not a good fit. We're launching a higher prized plan that has more memory for such things.
vishnukool
·5 か月前·議論
Yes exactly! Although we've launched a Claude Skill to help setup OpenClaw! So Agent 37 is literally the easiest Openclaw setup at this point :)
vishnukool
·5 か月前·議論
Absolutley! We do have some metrics like, when a user interacts with a skill or not, and so that's a signal
vishnukool
·5 か月前·議論
Yes, once we have a large enough numbers to justify that we'll factor that into the search results quality
vishnukool
·5 か月前·議論
Ah that's a good point, I think I could introduce some kind of time decay by also factoring in last updated repo time into the search priority.
vishnukool
·5 か月前·議論
Great point, we de-duplicate the search results by Repository Id. that largely filters out content from the same person , and note that search prioritizes github stars, so low quality one's get pushed to the bottom
vishnukool
·5 か月前·議論
Thank you! We have limits around usage. Also as a startup we have a lot of Gemini credits from Google, so that helps in offering it. Not to mention the gemini 3 flash that it's running on is dirt cheap.

Regarding low quality skills, our search only surfaces top starrted and forked skills, so that largely addresses that. Kinda like google page ranking. You'll see that whatever you search for, you tend to only get high quality skills first.
vishnukool
·5 か月前·議論
Yup we actually backup data in a separate partition per container. So it survives restarts and even accidental deletions.
vishnukool
·5 か月前·議論
Thanks! At the moment no, but down the line I imagine we can expose it if this is useful
vishnukool
·5 か月前·議論
We do back up data, although it's manual. The docker instance home directory and homebrew are backed up in a separate partition. So it survices restarts and container updates.
vishnukool
·5 か月前·議論
SO far pretty good! Turns out these things are mostly idle
vishnukool
·5 か月前·議論
We only allow ttyd not ssh, so users only have access to their individual containers and isolated from the host. But inside the container they can do whatever they'd want. There are also caps on CPUs and resource and PID limits so as to avoid noisy neighbor situations
vishnukool
·5 か月前·議論
True but Unfortunately, it's expensive to run VMs that are stateful and ongoing. In a way the 99 cents is just gate keeping really interested people vs others.
vishnukool
·5 か月前·議論
thanks!