skdotdan

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.

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

Edited

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

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

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.

What do you mean by “true” RL?

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

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

Cool! Thanks!

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.

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.

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.

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

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

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.

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

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.

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.

No one said it was. What some researchers hypothesize is that at the current rate of improvement, it wouldn't be especially unreasonable to expect AGI at GPT-N.

Could you share more details about it? Is your code open source?

YouTube ads are way more disruptive because they have to interrupt the video you are playing for at least a few seconds.

The moat is network effects, not the hosting service. GitHub is indeed a potential competitor but, again, you are just thinking about the hosting, while Huggingface provides an API compatible with all the uploaded models and datasets. GitHub would have to create their own API and then hope that users would switch to their service.

I don't think OpenAI is a valid comparison. Huggingface's mission, unlike in the case of OpenAI, is not training models, but being the standard service for sharing them. The vast majority of models and datasets available at the Huggingface Hub have been provided by third-party companies or researchers. They aim to be the Github of ML models and data, not an AI-building startup.

I wonder whether Bezos is feeling envious (in the good sense of the word). Wouldn't it be cool a new Space Race between SpaceX, Blue Origin, and Boeing?

AFAIK they used half-precision (Float16)

Never heard of them, thanks!

Thanks for your comment. I don't think it's that hard.

Take a middle/high-end smartphone phone. Install something like Maru OS (but preinstalled and with OEM support). That's it.

I agree with the cooling problems, but a desktop browser and Unix terminal would be enough, and these apps are not that demanding for the CPU.