My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried.
There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person does. But I'm finding that these Gemini models are finally able to replace searches and stackoverflow for a lot of my day-to-day programming.
Re hallucinating APIs that don't exist - I find this with Golang sometimes. I wonder if it's because the training data doesn't just consist of all the docs and source code, but potentially feature proposals that never made it into the language.
Regexes are another area where I can't get much help from LLMs. If it's something common like a phone number, that's fine. But anything novel it seems to have trouble. It will spit out junk very confidently.
Children’s books are some of the most wonderful little pieces of art; art that nurtures, entertains, educates and instills both moral compasses and working funny bones. All of our lives have been enriched by them. Some children’s stories continue to enrich us for all of our lives.
This doesn’t just steal work from those artists working today, but it steals from every artist who came before. It adds nothing to humanity; it robs so much.
It also destroys nature to do it. It robs from the world and worsens humanity.
Why do it? Money? Infamy? Internet points?
Please delete the project and do something worthwhile.
He created something and shared it with the world. It's not to your taste and that's fine. But don't knock someone down for having a red hot go at something.