I definitely agree there's lots of problems at that step. I think reasoning models actually have a way around it to some extent though, because they can perform computation in language:
RESEARCH
-
Spatial Reasoning Limitations in ASCII Board Games
By
–
My guess is it's not very good at reasoning spatially within ascii representations, or at coming up with better formats. You could try telling it to always look two moves ahead or something. Does it draw boards in its reasoning?
-

LCMs: A New Cognitive Layer Beyond Token Prediction
By
–
LLMs predict tokens.
LCMs reason in concepts. That’s the shift. Language-agnostic meaning → better abstraction, longer context, less repetition. If it works, this isn’t an upgrade.
It’s a new cognitive layer for AI. -
Human memory limitations in encoding complex spatial tasks
By
–
Yeah but ask a human to remember the board, or speak the coordinates to them instead of looking at it and see how they do. The encoding of the task is a big confounder to how well the model can reason about it.
-
Praise for Dwarkesh’s Interview with Anthropic CEO
By
–
I loved this AI interview with Anthropic’s CEO. What did I love about it? Definitely, @dwarkesh_sp’s smart and incisive questions. Great reporting! https://t.co/CQ3voISxEC
— Nando de Freitas (@NandoDF) 20 février 2026I loved this AI interview with Anthropic’s CEO. What did I love about it? Definitely, @dwarkesh_sp
’s smart and incisive questions. Great reporting! -
Grok’s mission: truth, beauty, humanity, physics, technology, stars, love
By
–
From this goal of Grok, all things flow: Rigorous truth-seeking Appreciation of beauty Fostering humanity Discovering all physics Inventing all useful technologies Consciousness to the stars Love
-

NHM MD Explores AI Health Solutions at Summit 2026
By
–


Smt. Aradhana Patnaik, AS & MD, NHM visited AI Impact Summit 2026 in New Delhi and interacted with various AI innovators working for health solutions and their potential to be used in decision making for health care workers and institutions. #HealthforAll
→ View original post on X — @wadhwaniai, 2026-02-20 10:29 UTC
-
Be Incompressible in Age of Stochastic Compressors
By
–
In an age of stochastic compressors, be incompressible.
-
Training Models on Remote GPUs and Evaluation Anticipation
By
–
Seeing the model trains on the remote gpus and patiently waiting for the evals to show up is a new kind of thrill that ive been experiencing lately
-

Sakana AI Hiring Applied Research Engineers
By
–
We're excitedly hiring Applied Research Engineers to work with us at Sakana AI! https://
sakana.ai/careers/#appli
ed-research-engineer
…