When humans sometimes act like confused language models.| blog.sshh.io
Some opinions on what the future might look like for jobs, AI, and software engineering.| Shrivu’s Substack
Scaling LLM-based agents to handle complex problems reliably.| blog.sshh.io
Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing wrong—how come some …| Simon Willison’s Weblog
Google’s new AI Overview feature is telling users a whole bunch of wrong answers.| The Verge
