Detailed analysis of Roose’s essay on coding: https://
open.substack.com/pub/garymarcus
/p/decoding-and-debunking-hard-forks
…
LLMS
-
Roose’s Coding Essay Analysis: Decoding Hard Forks
By
–
-
LLMs Will Easily Generate Educational Videos with Code-Based Animations
By
–
Actually, I think this will be the easiest kind of educational video to be generated by LLMs. That's because I believe (pls correct me if I'm wrong) the animations are code generated.
-
Reasoning LLMs: Multiple Implementation Approaches and Research
By
–
Not for now as there are ~100 different ways to implement reasoning. I've written about some of them here: https://
magazine.sebastianraschka.com/p/understandin
g-reasoning-llms
… and plan to follow-up with the latest research in a bit on my blog.
I think Unsloth is a great tool btw! -
LLM Training Easier Than OS and App Integration Challenges
By
–
sure, but the LLM is probably the easier part given that they already have trained a few; and pre-training+post-training usually takes ~3-6 months.
I thought the challenge is more on the integration with the OS and apps side. -
Evaluation Crisis: MMLU Obsolete, Need Better AI Metrics
By
–
My reaction is that there is an evaluation crisis. I don't really know what metrics to look at right now. MMLU was a good and useful for a few years but that's long over.
SWE-Bench Verified (real, practical, verified problems) I really like and is great but itself too narrow. -
Terminology Update: Test Set and Test Time Rebranding to Evals and Inference
By
–
test set and test time -> evals and inference
-
AI Code Generation Won’t Match Top Human Programmers by 2026
By
–
> and may match the best human coders by late 2026
No, unless you compare it to a human coder working offline. -
Quick Guide: Using Groq Models in Cursor AI for Fast Inference
By
–
Here's a quick walkthrough on how to get @GroqInc
— Groq Inc (@GroqInc) 2 mars 2025
models in @cursor_ai for fast inference speed. https://t.co/X8TM4dIomxHere's a quick walkthrough on how to get @GroqInc models in @cursor_ai for fast inference speed.
-
Five Years of LLM Improvements Ahead Without Further Progress
By
–
Good highlights! I imagine there’s still many other creative, useful ideas and quality of life improvements. Even if all LLM progress was to stop today I feel like we’d still have like 5 years of these to really get through, internalize and spread.
-
Systematic Survey of Automatic Prompt Optimization Methods
By
–
9). A Systematic Survey of Prompt Optimization This paper offers a comprehensive survey of Automatic Prompt Optimization (APO)—defining its scope, presenting a unifying 5-part framework, categorizing existing methods,…