justaregulardev

I've been experimenting with Claude a lot lately (like everyone else) and this post summarizes some of my current thoughts. Following up from the post, I'm not yet sure what the solution is to validation. It could be formal verification, although that's still dependent on having a perfect specification. Another method might simply be for harnesses to have a validation keyword that pushes them to validate after certain operations. Curious to hear your thoughts!

The ability to have models that can run on resource-constrained devices does feel like a strong direction for ML to go in and could lead to greater user privacy. However, I’m unconvinced by the IoT-aspect of this tech. In many ways, it feels like IoT has “failed” to be as popular with consumers as expected and feels overhyped. Will adding ML to IoT devices really make a difference?

This changes everything and seems like a perfect logical step from where we were. LLMs have this fantastic capacity to understand human language, but their abilities were severely limited without access to the external world. Before, I felt ChatGPT was just a cool toy. Now that ChatGPT has plugins, the sky’s the limit. I think this could the “killer app” for LLMs.

The emacs comparison definitely feels apt. Being able to simply use JavaScript and CSS to make changes to the editor made it feel so powerful. Maybe I just need to get around to learning elisp (or find an elisp-JavaScript binding…)

Here’s an article from TechCrunch (https://techcrunch.com/2019/10/02/tiny-acquires-meteor/) on the acquisition of Meteor by Tiny Capital