A recipe for frontier model post-training
Apple, Meta, and Nvidia all agree — synthetic data, iterative training, human preference labels, and lots of filtering.
Interconnects
354 posts
Interconnects
@interconnectsai
What you need to know about AI research trends, from @natolambert
Wednesday mornings weekly, sometimes extra posts.
Joined June 2023
- OpenAI's o1 using "search" was a PSYOP How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
- Synthetic data: Anthropic’s CAI, from fine-tuning to pretraining, OpenAI’s Superalignment, tips, types, and open examples Synthetic data is the accelerator of the next phase of AI — what it is and what it means.
- Reverse engineering OpenAI’s o1 What productionizing test-time compute shows us about the future of AI. Exploration has landed in language model training.
- China's Top 19 Open Model Labs We ranked all the organizations in China releasing open models, from the top of DeepSeek to small, newer academic labs making waves with tech reports and niche models.
- OpenAI's o3: Over-optimization is back and weirder than ever Tools, true rewards, and a new direction for language models.
- An unexpected RL Renaissance New talk! Forecasting the Alpaca moment for reasoning models and why the new style of RL training is a far bigger deal than the emergence of RLHF. YouTube: youtube.com/watch?v=YXTYbr… Slides: docs.google.com/presentation/d… More info: interconnects.ai/p/an-unexpecte…
- OpenAI’s Strawberry, LM self-talk, inference scaling laws, and spending more on inference Whether or not scaling works, we should spend more on inference.
- Quick recap on the state of reasoning -- can LMs reason? How? My talk at the NeurIPS Latent Space live event (pre o3). Slides: docs.google.com/presentation/d… Post: interconnects.ai/p/the-state-of… YouTube: youtu.be/2pHE9L4ZZXM?si…
- This also means you can write off your Interconnects AI subscription. Not official tax advice.wow - $5k tax free for ai retooling
- We're all excited about the GPT-5 release. Here's a fun game for while you watch. Potential prizes coming later! Livestream links coming soon.
- Futures of the data foundry business model Scale AI’s future versus further scaling of language model performance. How Nvidia may take all the margins from the data market, too.
- The state of post-training in 2025 A re-record of my NeurIPS tutorial on language modeling (plus some added content). Blog + extra context: interconnects.ai/p/the-state-of… YouTube: youtu.be/6yIMb0K-aS4 Slides: docs.google.com/presentation/d…
- Model merging lessons in The Waifu Research Department When what seems like pure LLM black magic is actually supported by the literature.
