Boosted by jsonstein@masto.deoan.org ("Jeff Sonstein"):
jgordon@appdot.net ("John Gordon") wrote:
“Using LLMs to write code is difficult and unintuitive”
https://simonwillison.net/2025/Mar/11/using-llms-for-code/#atom-everything
An impressive tutorial on using 2025 tech. LLM capabilities vary by language and library so will change what is used.
“Don't fall into the trap of anthropomorphizing LLMs and assuming that failures which would discredit a human should discredit the machine in the same way.”