Gemini 3 Deep Think New from Google. They say it’s “built to push the frontier of intelligence and solve modern challenges across science, research, and engineering”. It drew me a really good SVG of a pelican riding a bicycle! I think this is the best one I’ve seen so far – here’s my previous collection. (And since it’s an FAQ, here’s my answer to What happens if AI labs train for pelicans riding bicycles?) Since it did so […]
An AI Agent Published a Hit Piece on Me Scott Shambaugh helps maintain the excellent and venerable matplotlib Python charting library, including taking on the thankless task of triaging and reviewing incoming pull requests. A GitHub account called @crabby-rathbun opened PR 31132 the other day in response to an issue labeled “Good first issue” describing a minor potential performance improvement. It was clearly AI generated – and crabby-rathbun’s profile has a suspicious sequence of Clawdbot/Moltbot/OpenClaw-adjacent crustacean 🦀 🦐 […]
Hybrid architectures combining state-space models with attention have achieved strong efficiency-quality tradeoffs, yet existing approaches either apply attention uniformly or learn static sparse patterns. This misses a key opportunity: emph{attention demand should decrease over time as recurring patterns become familiar}. We present a surprising finding from analyzing GPT-2 models: textbf{88%} of attention operations retrieve information already predictable from the model’s hidden state, and this redundancy does emph{not} decrease during training. Motivated by this observation, we introduce textbf{ours{}} (textbf{C}onsolidation-based […]
Convex Markov Games (cMGs) were recently introduced as a broad class of multi-agent learning problems that generalize Markov games to settings where strategic agents optimize general utilities beyond additive rewards. While cMGs expand the modeling frontier, their theoretical foundations, particularly the structure of Nash equilibria (NE) and guarantees for learning algorithms, are not yet well understood. In this work, we address these gaps for an extension of cMGs, which we term General Utility Markov Games (GUMGs), capturing new […]
In my post about my Showboat project I used the term “overseer” to refer to the person who manages a coding agent. It turns out that’s a term tied to slavery and plantation management. So that’s gross! I’ve edited that post to use “supervisor” instead, and I’ll be using that going forward. Tags: language
It’s been about a month since Health Secretary Robert F. Kennedy Jr.—an anti-vaccine activist and lawyer who has no background in medicine, health, or science—released dietary guidance for Americans. It’s going about as well as expected for a man who drinks raw milk, peddles beef tallow, swims in sewage-tainted water, and keeps roadkill meat in his freezer. That is to say, it’s going badly—so badly that even his favorite AI chatbot is openly defecting. Of course, this hasn’t […]
On-policy distillation (OPD), which aligns the student with the teacher’s logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy distillation and reinforcement learning (RL) paradigms. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model. Then, we propose the Generalized On-Policy Distillation […]
Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples are included, yet selection must remain cheap enough to run per query over large candidate pools. We propose Meta-Sel, a lightweight supervised meta-learning approach for intent classification that learns a fast, interpretable scoring function for (candidate, query) pairs from labeled training data. Meta-Sel constructs a meta-dataset by sampling pairs from the training split and […]
Hello! I am looking for research that has successfully applied AlphaZero/MuZero-style learning to sequential, perfect information, non-zero sum board games, e.g. Terra Mystica where the winning player is decided by a numerical score (associated with each player) at the end of the game, rather than the zero sum outcomes of games such as Chess, Shogi, Go, etc. I figure there must exist an approach that works for multi-agent (> 2 player) games. Any suggestions? Thank you submitted by […]
We study offline reinforcement learning under $Q^star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical attention. Our work is inspired by the following open question: "Are $Q^star$-realizability and Bellman completeness sufficient for sample-efficient offline RL under partial coverage?" We answer in the negative by establishing an information-theoretic lower bound. Going substantially beyond this, we introduce a general framework that characterizes the intrinsic complexity […]