David Courtis (@DavidCourtis) profile picture

MASc @UofT, Machine Learning + Reasoning

Toronto, ON
Joined September 2025
Photo by David Courtis (@DavidCourtis)Photo by David Courtis (@DavidCourtis)Photo by David Courtis (@DavidCourtis)Photo by David Courtis (@DavidCourtis)Photo by David Courtis (@DavidCourtis)
We just got the top community score on ARC-AGI-3's 25 public games: 78.4% and 160/183 levels cleared, where the best frontier LLM session scores 7.8%. No training or demonstrations allowed. Paper: arxiv.org/abs/2607.01531 Blog: david-courtis.github.io/opin… w/ @WenhaoLi29 @ScottSanner #AI #worldmodel #agentic #AGI @arcprize @fchollet
9
17
1
88
13,578
David Courtis retweeted
One application of weight-space programming is out-of-parameter (OOP) generalization: synthesizing programs for task parameters not seen during training. For example, after learning ARC-style tasks that move an object right by various distances, can we predict the weights of a Neural Program for an *unseen* distance at test time, zero-shot? We show this is possible with a symmetry-aware graph hypernetwork in our @yudongxuwil @lyeskhalil @ScottSanner ICLR 2026 work: openreview.net/forum?id=x7zO…
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
4
9
1
40
8,808
Learn more about our work at our blog, where we’ve deconstructed some empirical results about our system: david-courtis.github.io/opin… And read our full paper here: arxiv.org/abs/2607.01531 w/ @WenhaoLi29 @ScottSanner
7
323
Implementing this, OPINE-World reaches 78.4% on the 25 games, with near-human action efficiency on its 20 wins. The specific model we used scores 1.5% when it plays on its own (the current frontier LLM scores 7.8%). The most developed prior method, on comparable models at similar reasoning effort, peaks at 63.7%.
1
8
371
Specifically: 1) An LLM's internal world model cannot be inspected or trusted. We address this by having the agent write the game's dynamics as an object-oriented Python program, accepted when it perfectly models the world or addresses faults as a testable hypothesis. 2) LLMs explore blindly and fall into “hypothesis lock-in”. We address this with ontology error, a Bayesian measure of how much of the game the program still can't explain. The agent spends its moves where that score is highest.
1
10
434
We investigated and found that pure LLMs and existing approaches fail this benchmark for two reasons: their internal model cannot predict the world in an accurate but fault-tolerant manner, and they struggle with hypothesis generation and testing in unknown environments. We propose enhancements to address these shortcomings in our new paper “OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration” (arxiv.org/abs/2607.01531)
2
1
15
555