kagen (@kagnar_) 's Twitter Profile
kagen

@kagnar_

doing 0 to 1 @getodinai @nerobotai

ID: 277248112

calendar_today05-04-2011 00:27:19

775 Tweet

438 Takipçi

1,1K Takip Edilen

kagen (@kagnar_) 's Twitter Profile Photo

My biggest takeaway from using the Apple Vision Pro. I want eye tracking based navigation for my laptop. The efficiency gain is unparalleled. Ty Will Price

kagen (@kagnar_) 's Twitter Profile Photo

Had a chance to meet with him yesterday. Really productive call excited to see what we can accomplish in the near future.

kagen (@kagnar_) 's Twitter Profile Photo

The kicker for using pydantic in your pipelines is that all your copilots are much better at recommending code because they have full insight into the data structure. h/t jason liu for the help❤️

Marques Brownlee (@mkbhd) 's Twitter Profile Photo

Every single one of these videos is AI-generated, and if this doesn't concern you at least a little bit, nothing will The newest model: openai.com/sora (Remember Will Smith eating spaghetti? I have so many questions)

Shaun.AGI (@agishaun) 's Twitter Profile Photo

Here's one of proof in the tech report, Gemini team compared Gemini 1.0 pro w/ RAG v.s. Gemini 1.5 Pro. Gemini 1.5 outperform Gemini 1.0 + RAG RAG technics they used, TF-IDF database + Cosine similarity search + Rerank + Similar passages Note: TF-IDF database -

Here's one of proof in the tech report, Gemini team compared Gemini 1.0 pro w/ RAG v.s. Gemini 1.5 Pro. Gemini 1.5 outperform Gemini 1.0 + RAG

RAG technics they used,
TF-IDF database + Cosine similarity search + Rerank + Similar passages

Note: TF-IDF database -
Omar Khattab (@lateinteraction) 's Twitter Profile Photo

I always thought these remarks are not very serious but since they’re common it could be instructive to comment. Tradeoffs. Context (concatenation) & Retrieval pose fundamentally different tradeoffs in recall, precision, and latency/cost. You can’t “choose” between RAM and disk.

Rahul Behal (@rbehal1729) 's Twitter Profile Photo

Nero is seriously one of the most underrated AI products out there. kagen is way too busy building to advertise. We have an integration on Gumloop as well if you want a simple interface for it

jason liu - vacation mode (@jxnlco) 's Twitter Profile Photo

Open call. I’ll pay someone 400$ to make instructor support Claude function calling and that xml mess. Lmfao. With patch(create=) Just needs a PR with passing tests. Negotiable.

Anil Lulla (@anildelphi) 's Twitter Profile Photo

I got married last month, and spent the furthest time away from work during that period and the honeymoon Unplugging while we broke ATHs really helped me reflect on what I’ve learned up until this milestone and what’s important to me in life I wanted to share this publicly

I got married last month, and spent the furthest time away from work during that period and the honeymoon

Unplugging while we broke ATHs really helped me reflect on what I’ve learned up until this milestone and what’s important to me in life

I wanted to share this publicly