Analysis
Opinion, explainers and guides from people worth reading.
.png)
I Made Terrible Games With Google’s AI Playground
A long day’s haul in the video game slop mines.
A/B Blind Taste Test - Krea2-Turbo vs. Qwen-Image 2.1 Turbo
Since Qwen 2.1 Turbo dropped suddenly right after my last taste test, figured might as well do one for it as well.
I tested different Qwen 3.8 27B quants
There is a lot of discussion which quant to use.
[P] Pecision models that score every allowed label from the logits: Jebadiah v2.1 (27B, 9B), open weights and self-run benchmark results [P]
I've been building open models that treat a decision as a closed-set scoring problem rather than text generation.
Qwen3.8 27B addition in words
Research: Qwen3.8 27B addition in words
VideoLet Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
A financial agent invents answers, repeats tool calls and produces summaries that its own evaluations flag as wrong.
Refs
Give Claude better references for your videos
Childhood and Education #21: Grades and Standards
First you get to college via the wrong metrics, as previously discussed in #12.
Don’t be fooled—LLMs don’t reason
AlphaGo won the game, ultimately triumphing 4-1 over Lee Sedol, one of the greatest professional Go players of all time. “I thought AlphaGo was based on probability calculation and that it was merely a machine,” Lee said afterwards. “But when I saw this move, I changed my mind.
Qwen 3.8 27B Q5 vs Qwen 3.8 Next Q3_S for document analysis
So far I've been using Qwen 3.8 27B Q5 with a 150K context window, but I'm wondering whether I should switch to Qwen 3.8 Next Q3S, since it has much more knowledge and could extract data much better than the 27B.
Has machine learning research gotten more "wordy"? [D]
I feel like I am unable to digest most machine learning research these days.
pwasm 0.2a0
pwasm is one of my folly projects - an entirely vibe-coded pure Python WebAssembly engine that I built in January during my first bout of AI mania.
NeurIPS 2026 Paris complimentary registration already full. Did any Top Reviewers get a spot? [D]
Did any reviewers actually manage to secure a spot in Paris, or were all the available places already taken during the earlier registration rounds for SACs and ACs?
4090 VS 5090 MINIMAX H3 SPEED
To those who used to have a 4090, what percentage of speed improvement have you noticed after upgrading to a 5090?
Do I need to do anything now to use an ARR August review for NAACL 2027? [D]
If we want to commit to NAACL 2027 instead of EACL, do we need to do anything with the August ARR submission now, or can we simply wait and commit it when the NAACL commitment site opens?
The Computer Game
Build the best computer, from stone tools to your own chips
GitGlow
Review your code and your agents' changes before you ship