HackerTrans
トップ新着トレンドコメント過去質問紹介求人

abhis3798

no profile record

投稿

OpenIQ - Building a product engineering muscle in the age of agents

abhirame.github.io
2 ポイント·投稿者 abhis3798·2 か月前·0 コメント

Soul.md

3798.substack.com
2 ポイント·投稿者 abhis3798·2 か月前·0 コメント

Agents over Bubbles

stratechery.com
5 ポイント·投稿者 abhis3798·4 か月前·0 コメント

コメント

abhis3798
·2 か月前·議論
Love this. I use a similar "ralph-loop" approach that starts with an approved plan and then hand it off to a coordinator which does it across 2 sessions (build and review for simplicity), with each session getting its own model.
abhis3798
·2 か月前·議論
That's interesting. I've been trying to build something similar as a side project: Hermes agent + plugins (MCP, skills, and agents) + a Postgres DB for auditing and state. The idea is essentially to make all of that a black box and present a simple “work queue” to a desk assistant.

Good validation that this is indeed a space the frontier firms are thinking about along similar lines.
abhis3798
·2 か月前·議論
If that's the only way you pay your bills then this article is not asking you to give away your software for free. It is for second jobbers.
abhis3798
·4 か月前·議論
I see remote MCP servers as a great interface to consume api responses. The idea that you essentially make your apis easily available to agents to bring in relevant context is a powerful one.

When folks say MCP is dead, I don't get it. What other alternatives exist in place of MCP? Arbitrary code via curl/sdks to call a remote endpoint?
abhis3798
·5 か月前·議論
On the other hand, my parents did not realise they needed to scroll down to read the article. :)
abhis3798
·8 か月前·議論
I am sure they do. This is a talk they gave on using AI to tackle security problems. https://youtu.be/JRvQGRqMazA?si=euwRGML-unsm59ZU
abhis3798
·昨年·議論
This is a good rule of thumb, but what would be a good response to have interfaces because, "what if a new scenario comes up in the future"?