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:
LLMS
-
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. -
Export your data and transfer to another LLM
By
–
But you can. Check settings – Data – Export Data. You can also export said data as a zip file and upload to the memory of another LLM
-
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
-
The AI-driven Cambrian explosion in software development
By
–
Picture the Cambrian explosion in software when it no longer has to be written by software engineers.
-
Leveraging domain expertise to guide AI models effectively
By
–
Yup. And if you have domain expertise you can really steer these models towards the right solutions w/o sweating the implementation. Really fucking fun
-
Comparing LLMs for creative orchestration and code generation
By
–
I find Claude to be best for creative thinking and orchestration — like codex 5.3 and Gemini 3.1 to write the code
-
Building real-time geospatial tracking systems with Gemini and Claude
By
–
Between Gemini 3.1 and Claude 4.6 it's honestly wild what you can build. This feels like Google Earth and Palantir had a baby.
— Bilawal Sidhu (@bilawalsidhu) 20 février 2026
Made this with all the geospatial bells and whistles — real time plane & satellite tracking, real traffic cams in Austin, and even got a traffic system… pic.twitter.com/GXpizt0TLnBetween Gemini 3.1 and Claude 4.6 it's honestly wild what you can build. This feels like Google Earth and Palantir had a baby. Made this with all the geospatial bells and whistles — real time plane & satellite tracking, real traffic cams in Austin, and even got a traffic system
-

Gemini 3.1 Pro Launches with Major Reasoning Improvements
By
–
Gemini 3.1 pro is here 😁 Just one week after the Gemini 3 Deep Think launch, the core model/intelligence powering it all is shipped! Sundar Pichai (@sundarpichai) Gemini 3.1 Pro is here. Hitting 77.1% on ARC-AGI-2, it’s a step forward in core reasoning (more than 2x 3 Pro). With a more capable baseline, it’s great for super complex tasks like visualizing difficult concepts, synthesizing data into a single view, or bringing creative projects to life. We’re shipping 3.1 Pro across our consumer and developer products to bring this underlying leap in intelligence to your everyday applications right away. Rolling out now to: – Developers in preview via the Gemini API in @GoogleAIStudio – Enterprises in Vertex AI and Gemini Enterprise – Everyone through the @Geminiapp and @NotebookLM — https://nitter.net/sundarpichai/status/2024516418855981298#m