Tagide

Or How LLM Hallucinations Become Human Hallucinations By Crista V.

This post comes on the heels of a Tweeter-conversation I had yesterday, where a colleague asserted that no evidence is needed to know that human reviewers are much better than LLMs at detecting things that read well but are fatally flawed.

If you’ve seen my previous 3 posts, you know what this one is going to cover… After seeing ChatGPT solve the clone detection problem, generate a tokenizer in Python, and perform tokenization from a few examples and informal explanations, this morning I wa…

Yesterday, I had a conversation with ChatGPT where it helped me write a completely functional tokenizer in Python for the Lox programming language.

This morning I decided to test how good ChatGPT is at generating a non-trivial piece of code.

I have been playing with ChatGPT, a little bit every morning, close to the things I know best.

Due to the COVID situation, I have, in the past 2 weeks, been approached by several people whose conferences are being cancelled asking me for advice on how to organize a virtual conference.

I have a very conflicted relationship with airplane travel.

The Art, Science, and Engineering of Programming journal is teaming up with the Onward!

Big data is everywhere.