Full Width 
Shortcuts 
Sign Up 
Log In 
Articles 
Reading List More from seangoedecke.com RSS feed
When you should lie to the language model
Here’s an unreasonably effective trick for working with AIs: always pretend that your work was produced by someone else. The problem is that…
3 days ago
•
4 votes
A practical guide to coding securely with LLMs
Writing code with LLMs is fundamentally different from other ways of programming. LLMs are often non-deterministic and always unpredictable…
a week ago
•
10 votes
Why is lmarena.ai dominated by slop?
When LMSYS (aka LMArena, aka Chatbot Arena) first blew up, I thought it was the best way possible of determining which LLM really was the…
a week ago
•
8 votes
Designing software that could possibly work
Whenever anyone describes a piece of software to me, I think about how I would build it. Software engineers do this a lot, but many of them…
a week ago
•
10 votes
More in AI
OpenAI’s dirty December o3 demo doesn’t readily replicate
Don’t believe everything you see
21 hours ago
•
3 votes
New Results of State-of-the-art LLMs on 4 Political Orientation Tests
One model appears closer to the center than the rest
2 days ago
•
3 votes
What LLMs Will Do To Jobs: All You Need is an Oracle
LLMs are Mainly Tools That Enhance Experts
2 days ago
•
5 votes
