It’s interesting to see something that’s so complex reduced to its simplest form.
New art project.
Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further.
gist.github.com/karpathy/862…
301
I really enjoyed this talk from @3blue1brown where he gives an accessible way to visualize transformers and attention.
1
163
Shane Lawrence retweeted
Want to make MCP tools more interactive? @janakiramm explains how to integrate elicitation so your apps can accept real user input instead of fixed parameters.
thenewstack.io/how-to-implem…
TIL I can immediately escape a hung SSH session! I don’t need to repeatedly mash Ctrl+C, Ctrl+Z, and Ctrl+Shift+6 before giving up and closing the terminal. I can press Enter ~ . and it just works.
1
217
My UniFi U6 Enterprise AP was getting exactly 100 Mbps on 6 GHz. The 5 GHz band was much faster!
1
2
254
After a lot of dead-ends and the usual turning it off and back on again, I found a bug. No matter what channel width I set, the 6 GHz band was stuck using 20 MHz.
1
145
At the conference:
AI’s different because is non-deterministic and we need more interpretability research to understand what it’s doing.
Debugging my own code:
It worked on my machine. I’ll add print statements everywhere and try to figure out what it’s doing.
121
“In a particularly thought-provoking session, Shane Lawrence, senior staff engineer at Shopify, discussed security threats to AI models.”
Thanks @camillecrowelee!
1
1
116
It was a lot of fun to present this demo and talk about AI (and a bit of Supply Chain) today at #KubeCon!
Mind-blowing talk by @shaneplawrence at Cloud Native AI Day at #KubeCon!
He shared a live demo showing how AI can accidentally SPILL SECRETS (!!) and how to deal with these new challenges!
This is what makes KubeCon fun!! Just cool ideas everywhere 💫
Shane Lawrence retweeted
Types of controls:
1. Controls as code.
2. Controls as bureaucracy.
3. Other?
Has anyone generalized a deobfuscator that can be built into pipelines yet?
ChatGPT 3.5 misses it, but ChatGPT 4 is pretty good at flagging parts of the xz compromise even without full context. "This script is highly suspicious in nature and appears to be designed to execute potentially malicious code hidden within compressed files..."
1
4
706










