Has anyone else noticed Facebook getting more aggressive in its attempts to get you back on the platform? Just this morning, I actually received an SMS about one of my old uni professors sharing a link. And that's on top of more popup notifications, emails, etc.
Any chance you could share the GPT-3 settings you used to get that result? I've been playing around to try and get the same thing -- closest I've gotten is having it spit out other (correct) chapter names in the same format.
I've heard about this for years, but I've never had it happen, and I don't know anyone else who's experienced it. I don't doubt it happens, but what could cause such a discrepancy in the time it takes to degrade?
Hi, everyone. This is a platform I've been working on for awhile. We offer easy serverless hosting of models with usage-based pricing. Some out-of-the-box models/tasks are included, and they can be used immediately after signing up with zero configuration needed.
Our goal is to make machine learning more accessible to all developers, without requiring expertise in infrastructure or data science.
I'm happy to answer any questions if you've got them.
+1 for VCV Rack. It's an amazing piece of software, and entirely mitigates the up-front cost issues that come along with diving into modular synthesis.
This reminds me somewhat of Project Ara[0], that modular phone project Google was looking into. Interesting to see a similar concept (albeit more niche) being built out further, especially since it's not tied to any major company. Looks quite cool.
This is a Python library I've been co-authoring for the last few months, with the goal being to make finetuning and using models as easy as possible for devs, even without extensive ML experience.
We've currently got support for text and image-based tasks, with wrappers around models like Google's T5, OpenAI's CLIP, and Facebook's BART, among others (with more on the way).
We've got some features that make deployment for production easy, but for full transparency, deployment is through a paid platform [0] we've developed that is by no means necessary to use the library.
We're happy with the progress we've made, but we're curious to hear what people think so we can improve it in the future.