> hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful.
If a driver cannot react fast enough to someone on a crosswalk, then the driver is driving too fast. Cyclists don't throw themselves right in front of a moving car. It's a lot safer to cross on a crosswalk, even on a bike.
I'm happy to read this. I had to use GraphQL once in an old job and I hated, hated the freaking thing with a passion, but there was so much hype about it I concluded the problem with it was caused by myself, a getting older and more close minded self. I see now that GraphQL may not be that wonderful, after all.
Wouldn't this kind of problem be a perfect match for machine learning? It would have a huge dataset to learn from. Why isn't it happening or what prevents AI tech from forecasting the weather?
No. We "moved to the cloud", everything became a "microservice", put together using existing libs, and I now spend my time trying to figure out why things running in obscure black boxes stop working in the middle of the night. I hate it. I wish I was coding instead of pushing buttons.
It looks like outdated shit, and that makes me happy. I worked on CDE HP systems for many years, and I liked it. The fact that it looks bad now is proof that we've come a long way and that great progress has been made, hence the happiness.
A lot of people I work with in Montréal only speak English. It's not a big deal because everyone else is bilingual so the communication isn't broken. The main problem is when it comes to finding a job - speaking French and English is usually a core requirement. If you don't, you'll have to compensate.