skdotdan

no profile record

comments

last yeardiscuss

Personally, I use LLMs to write code that I would have never bothered writing in the first place. For example, I hate web front-end development. I'm not a web dev, but sometimes it's cool to show visual demos or websites. Without LLMs, I wouldn't have bothered creating those, because I wouldn't have had the time anyway, so in that case, it's a net positive.

I don't use LLMs for my main pieces of work exactly due to the issues described by the author of the blogpost.

last yeardiscuss

Not true. VAT does way less economic damage. Tariffs introduce massive distortions in the market.

2 years agodiscuss

Edited

2 years agodiscuss

As an anecdotal data point, I’m happier than in my early and mid 20s, and I have hope for my 30s.

2 years agodiscuss

This is not what hallucination means in the pre-LLM machine learning literature.

2 years agodiscuss

It’s used incorrectly. Hallucination has (or used to have) a very specific meaning in machine learning. All hallucinations are errors but not all errors are hallucinations.

2 years agodiscuss

What do you mean by “true” RL?

2 years agodiscuss

The way I see it hallucination and factual error are particular cases of incorrect answer.

3 years agodiscuss

Deepmind tried something similar in 2018 https://deepmind.google/discover/blog/learning-to-write-prog...

3 years agodiscuss

Cool! Thanks!

3 years agodiscuss

Rust is great, but one thing I’d like to see is an interpreted, dynamic, less strict version of it that could be used for prototyping and gradually typed into compiling Rust code. In other words, a new programming language doing to Rust the reverse of what Mojo is trying to do to Python.

3 years agodiscuss

I believe the main Mojo use cases are scenarios in which you'd need dependencies anyway. Code that you can't write in Python due to performance concerns, so you'd need to call C/C++/Rust/CUDA/Triton/etc anyway.

3 years agodiscuss

I'm sure Chapel has its merits, but one of the main selling points of Mojo is the aspiration to be part of the Python ecosystem, and so far I haven't seen any other programming language offering a similar promise, other than Python itself coupled with DSLs or other extensions for high performance.

3 years agodiscuss

The term of “hallucination” referred to generative ML models have been used in the literature for years, at least since GANs.L

3 years agodiscuss

I graduated in 2019 and studied Prolog in my third year.

3 years agodiscuss

Looks great! Rust is the wrong language for developing ML models, but it has a clear potential for being the best one for deploying them.

3 years agodiscuss

Aren’t iMessage and FaceTime irrelevant outside from the US? I don’t know a single non-American person who uses them.

3 years agodiscuss

Not an expert in East Asian languages, but GPT tokenizers are generally byte-based. Meaning that the basic unit to do the merges is a single byte, not a character.

3 years agodiscuss

I’d add that while languages should die, code written in it shouldn’t. So, even if a language is deprecated, we still should be able to run, call and interoperate with all the legacy code that was written in it.