🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Wonder what happened with the LinkedIn recsys algo that now prioritizes 2-3w old posts that I have seen before. Congratulations!

% lift in accuracy by system_prompt.upper()

I compiled @bclaive 's opening lesson of our mini RAG optimization & eval course into these high density notes. You can consume the 30 minute talk in a few minutes in this format! 🏎️ Do ya'll like this format? LMK! I personally prefer this! hamel.dev/notes/llm/rag/…

Your AI Needs a Computer

Perfect blog post, not too long.

Have anyone done the story about what happened at Meta with their LLM efforts, notable people like Rohan from GM joined and exited just after a few months. Llama 4 released on a weekend. Now this hiring frenzy and all. Would love to read the backstory.

OpenAI researchers opening their LinkedIn this AM

«Experiments demonstrate that MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results» More interesting work on VLM-based embedding models!

I don’t have a horse in this race but - even if ps is using local disks, it’s still the same order of magnitude on qps - you pay for tightly coupling (always on) Also, depending on how this benchmark is done, it might just be measuring latency if you used a fixed number of

Opening with «In the realm of» makes me close the tab quicker than you can say chat

Extremely useful annotation! Thanks for sharing Hamel Husain and Nandan Thakur 🍻

«As an early stage employee, you should know how much you own»