built a weird little library last friday night. it uses LLMs to auto-generate JavaScript class methods at runtime; no need to define the method ahead of time—just decorate your class, call whatever you want, and the model figures it out on the fly.
it uses `Proxy`s, and pipes the class definition and the call example to the LLM for it to generate a valid method.
of course it was not built for production use, but it was a fun exploration. would love to hear your thoughts!
It'd be helpful if they exposed a summary of the chain-of-thought response instead. That way they'd not be leaking the actual tokens, but you'd still be able to understand the outline of the process. And, hopefully, understand where it went wrong.
Just to add to the reply, the AdS/CFT correspondence (aka Maldacena duality) was proposed by Juan Maldacena, one of the authors of this paper (Humanly traversable wormholes).
I felt the same way about Netflix when it first started. Now, there are dozens of competitors with different catalogues, making piracy enticing for people once again.
I recommend you the story "The Last Question", by Isaac Asimov[0], one of my favourite stories of all time. It's about how the question about reverting the direction of the entropy keeps rising on people, throughout the life of the universe.
My country (Argentina) has a lottery(esque?) approach to giving work visas for the US, so basically: even with company support, work visas are subject to probability (~30% chance of getting it for a given year). Do you have experience, or do you know, how companies handle hires from countries with this methodology?
The 10k hours rule is actually a misunderstanding from a paper on violin practice by Anders Ericsson. An error that the author himself explains in his book Peak: Secrets from the New Science of Expertise. It doesn't mean that you can't learn something to mastery in 10k hours or less. It just means that 10k hours is kind of an invented number. Some skills require more time, some less, but all of them require purposeful practice.
This is not intended in any way to be used in a production environment. It is just a cool experiment to show javascript versatility :). Your points are entirely valid!
I agree with you about the complexity of a mvp. It indeed may vary. However a mvp is about testing an hypothesis, not building a simple version of a product.
Maybe an mvp for a complex product is just a landing page explaining features with a buy button, built in under 2 hours using optimizely.
Again, it depends on the hypothesis. So, in this way, I differ with you when you say getting out a mvp asap doesn't make sense. Because validating you hypothesis is what you want to make as fast as possible. But then, launching as fast as possible doesn't imply necessarily launching fast.
I think the whole point of an MVP is to validate the hypotesis you make about your users.
In your case for example, do you know who your users are? Are they entrepreneurs? Current software developers? Anyhow, who is going to use your service?
I'm not trying here to undermine your project since it indeed sounds pretty awesome, but to reinstate why the whole mvp movement has a reason to be.
it uses `Proxy`s, and pipes the class definition and the call example to the LLM for it to generate a valid method.
of course it was not built for production use, but it was a fun exploration. would love to hear your thoughts!