Nathan Lambert on AI

Very happy to show that we can do RL finetuning on 405B models with open-source code, beat Llama 405B instruct with their base model, and beat DeepSeek V3 too. Enjoy building off this teams hard work. Here's Tulu 3 405B. A holiday present from @hamishivi, @vwxyzjn and team.

658 likes26 repliesPosted Jan 30, 2025

Remix this post

Your note

Private to you, and used when you remix this post.

Viral score

Based on absolute engagement — the platform doesn’t expose follower counts here, so large accounts score higher.

From likes, comments.

Why it worked

Leads with a specific number, which is concrete enough to be worth a second of attention.
Uses concrete numbers instead of vague claims, which makes it credible and quotable.
Points at real customers, users or results as evidence rather than assertion.
Ends on a short line that is easy to quote and repeat.
Written from experience rather than as advice, which is harder to argue with.
Short enough to read in full without expanding, which removes a step before the point lands.

The mechanics

Hook: Leads with a number
Structure: Hook → Landing
Style: Conversational paragraphs at a steady pace.
Tone: corporate
Mechanisms: Specificity, Social proof
Written for: People building with AI

Analysis by ViralLoop — not written by the original author.

Topics

AI Engineering Hiring

Post by Nathan Lambert on X