HackerTrans
トップ新着トレンドコメント過去質問紹介求人

zkoch

no profile record

投稿

Beyond Benchmark Maxxing: Measuring Open Source Models as Real-World Agents

ultravox.ai
1 ポイント·投稿者 zkoch·11 か月前·0 コメント

Ultravox: An open-weight alternative to GPT-4o Realtime

ultravox.ai
8 ポイント·投稿者 zkoch·2 年前·1 コメント

コメント

zkoch
·11 か月前·議論
I love working in Zed. It really is a delight to use, and I think the Agentic coding integration is really well done. I'm excited to see them investing in this space more.

I understand people's concerns about VC funding, but I think building quality products takes capital. The funding is still relatively small, especially when you compare it to players like Cursor, etc. And I think Zed is a much, much better product!

Zed being OSS is a gift to the community, and I suspect DeltaDB will be as well. And as others have said, Nathan (CEO) is a delightful human.

Congrats, Zed!
zkoch
·昨年·議論
I think it is a very common misconception (by consumers or businesses trying to use LLMs) that fine tuning can be used to inject new knowledge. I'm not sure many of the fine-tuning platforms do much to disavow people of this notion.