PhD @MIT_SCC | Stochastics, Statistics, ML | BS @EmoryUniversity
Cambridge, MA
Joined July 2023
- Tweets4
- Following159
- Followers24
- Likes396
Kai retweeted
New Anthropic research: A global workspace in language models.
Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.
We found a strikingly similar divide inside Claude.
Kai retweeted
Thanks so much for featuring our work, ACE (Agentic Context Engineering) and Meta-Harness! @lilianweng
My bet: harness engineering is not only a test-time technique ---- the traces it produces can also serve as a data engine for model pre-/mid-training. Writing something up on this soon : )
Paper links
ACE: arxiv.org/abs/2510.04618
Meta-Harness: arxiv.org/abs/2603.28052
new post on harness engineering for AI self-improvement: lilianweng.github.io/posts/2…
It is hard to forecast how much the future of RSI will rely on harnesses. Likely harness engineering will evolve in the direction of self-improvement and enable auto-research, and, in turn, smarter models keeps harnesses simple.
Even when many harness improvement get eventually internalized into core model, the need to specify goals and context will not disappear.
Kai retweeted
🚨Exciting Faculty Positions @PennEngineers!
Join our AI for Science initiative backed by $750M investment & shape the future of scientific discovery through AI/ML, from materials design and drug discovery to autonomy and climate modeling.
✨Here's what we offer: