I'm not convinced LLMs can catch interesting deep patterns in their training data
@simonw
-
How to run local LLMs using uv and llm-mrchatterbox
By
–
If you have uv installed you can start a conversation (after a 2GB model download) directly like this: uvx –with llm-mrchatterbox llm chat -m mrchatterbox
-
New local 2GB nanochat model Mr. Chatterbox released
By
–
Mr. Chatterbox is a new 2GB nanochat model trained from scratch by Trip Venturella on "28,000 Victorian-era British texts published between 1837 and 1899" – I released an llm-mrchatterbox plugin which can run it locally on my Mac
-
User Upgrades Laptop with 128GB RAM for AI Workloads
By
–
My existing laptop was showing its age, and I think 128GB RAM will do me for quite a while
-
AI Models Master SwiftUI Development Without Xcode
By
–
I've been vibe coding SwiftUI menu bar apps for my new Mac, turns out Claude Opus 4.6 and GPT-5.4 are both competent at Swift programming, no need to even open Xcode!
-
Cybersecurity Strategy: Focus on Attack Response and Resilience
By
–
That is advice I gave a consulting client the other day: assume that you cannot prevent every attack from making it through, so focus your engineering efforts on what happens when an attack DOES get though
-
The Futility of Robust AI Jailbreaking Prevention Measures
By
–
To me this mostly illustrates the futility of robust jailbreaking prevention
-
Mac Compatibility Question for Cross-Platform Software Solution
By
–
"Runs on everything from edge to server" – does everything include Macs?
-
Latest AI Models Excel at Following Instructions
By
–
Would need to see your prompts – I've found the latest models are fantastic at instruction following
-
Cheap Code Economics and Over-Testing Opportunities
By
–
Yeah, I agree with that – but I do think that the new economics of cheap code open up opportunities for over-testing things in a way that didn't make sense before Open question if it's a good idea to do that though!