Want models to translate in the style you actually like? Our paper is here! See you in Marocco! 🇲🇦

You can easily save up to 65% of compute while improving performance on reasoning tasks 🤯 👀 Meet EAGer: We show that monitoring token-level uncertainty lets LLMs allocate compute dynamically - spending MORE on hard problems, LESS on easy ones. 🧵👇

I’ll be attending the NEMI 2025 workshop this Friday and presenting a poster👇. Happy to chat about cool interpretability stuff there!

📢 New paper: Applied interpretability 🤝 MT personalization! We steer LLM generations to mimic human translator styles on literary novels in 7 languages. 📚 SAE steering can beat few-shot prompting, leading to better personalization while maintaining quality. 🧵1/

Now on 🦋!

It was great, I'm starting to get tickets for next year!