How well does a model have to be able to do this? It would probably be possible to hack something up to do this with Langchain today, it would just not be particularly good.

@Thomas42 Presumably it would have to be good enough that many companies start actually using AI coders to do tasks that they once hired entry-level just-out-of-undergrad humans to do. So, the AI wouldn't have to be quite as good as existing entry-level coders (since the AI would be much cheaper, so somewhat worse performance might be an acceptable tradeoff), but it would have to be kinda close (because the kind of coder you could hack up today, AutoGPT-style, probably wouldn't actually save enough time/effort that it would be adopted by many companies).

@Thomas42 As well as an entry-level coder. The most straightforward way for this to resolve is if tech companies start using AI to do entry-level coder work.

@vluzko "The most straightforward way for this to resolve is if tech companies start using AI to do entry-level coder work."
Seems nebulous to me. I imagine the default state is that, "At least some companies have full-AI-loops in their systems, but they don't work too well. They don't 1-1 replace real people, but they help amplify them."

There's already a company that does AI PRs for codebases. It's not too hard to do a shitty job at the basics, and for that to be used at least somewhat.

Is it still YES if multiple AI models are involved? For example, if there is a model to take an issue and write out a description of the needed changes, another to write the code, another to write the tests, another to make changes in response to review, etc.

@hyperion Good question: still YES.

Will there be entry-level AI coders by 2026?, 8k, beautiful, illustration, trending on art station, picture of the day, epic composition