Sycophancy is the first LLM "dark pattern"(seangoedecke.com)

135 points by jxmorris12 10 months ago | 81 comments

Should LLMs just treat text content as an image?(seangoedecke.com)

159 points by ingve 1 year ago | 94 comments

OpenAI's new open-source model is basically Phi-5(seangoedecke.com)

372 points by emschwartz 1 year ago | 200 comments

Sean Goedecke's blog post arguing that OpenAI's open-weight gpt-oss models resemble Microsoft's Phi series, strong on benchmarks but weak on out-of-domain knowledge.

Diffusion models explained simply(seangoedecke.com)

123 points by onnnon 1 year ago | 25 comments

Which programming languages are most token-efficient?(martinalderson.com)

87 points by tehnub 9 months ago | 61 comments

LLMs reward expertise(seangoedecke.com)

1278 points by MaxMussio 2 months ago | 527 comments

Blog post by Sean Goedecke arguing that the most important skill in prompting LLMs is expertise in the domain being prompted for.