Re:I worry our Copilot is leaving some passengers behind
by EscargotCult on Saturday February 17, 2024 @06:27PM
(#39414537)
> Copilot is bad at accessibility because web engineers are bad at accessibility. All of the bad habits in this post were learned from its training data.
100%, and this is why Copilot is damn-near unusable for Bash scripting (yeah, the real problem is Bash scripting, use a better scripting language etc etc, but I do it, you've probably done it, and we've all definitely worked with codebases with Bash script linchpins) - there's a lot of bad Bash out there.
That's not to say this can't be fixed: a recurring lesson of LLMs is that the quality of the training data is /everything/. OpenAI made their models better at chess by feeding in higher quality chess data - they could absolutely make it better at accessible frontend code by curating and boosting better code examples.
I doubt they'll do that any time soon, purely because there are so many other training data projects they could take on.
Thankfully we aren't nearly as dependent on a few closed research labs as we used to be.
It would be very exciting to see fine-tuned openly licensed models that target exactly this kind of improvement.