🔥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

Honestly, no... My APM is already far below competitive levels without needing to dictate 😅 Cool tech though!

Reasoning models do great at what they're trained to do... crushing quantitative benchmarks! But, as we have also observed, that does not translate to open-ended or multi-turn or creative tasks.

Defended 🎉🎓 Big thanks to Roy Fox (@[email protected]), Sameer Singh, and labmates for their mentorship and support over the past 5 years!

Any way to test this on BALROG? Davide Paglieri

Gamified prompt hacking is its own subgenre at this point. Suck Up! was still my favorite.

I've been thinking that something like this would be great applied to dialogue in genAI games 💡

MINDcraft is special as it has already existed as OSS on GitHub for a while and built up a great community of thousands of users, sparking many unique benchmarks. Today we bring it to the AI/RL/LLM research communities as a scientifically rigorous env github.com/kolbytn/mindcr…

It was great collaborating with Isadora White and the folks at UCSD to bring MINDcraft to the research community. Max | Emergent Garden and I have worked hard to make the best AI minecraft bots loved by players and researchers alike!

Check out the latest from our #AIResearch team, in this fascinating blog written by our own Kolby Nottingham. #syntheticdata #DPO #rewardmodels #aigaming

AI Dungeon is hiring a Machine Learning Engineer to help with: model evaluation ⚖️ statistical testing 📊 tools and infrastructure 🏗️ dataset design 🎭 finetuning pipelines ⚡️ DM me your resume if interested!