> These ML-compilers are being overhyped. It's all the same trade-off as a traditional compiler

Funny you should say that. Because traditional compilers have been incredibly useful.

Right, but we still tend to sidestep the compiler and/or spend hours of human time tuning the input to get the right output for core kernels.

The people who build this all leave on October 15?

What could possibly go wrong with that?

Were you using the base model or the conversational model?

The post says:

The base model has no prompt format. Remember that it’s not a conversational model or trained with instructions, so don’t expect it to generate conversational responses—the pretrained model is a great platform for further finetuning, but you probably shouldn’t driectly use it out of the box.

I've tried AutoGPT agents about 10 times for tasks that seem like they'd be a good fit. That meaning they need to scrape current data, but otherwise they'd be possible for a person willing to put in some time to combine data sources.

An example is "create a table showing the current ratio of rental/sales prices (on a per square foot basis) for residential properties in the 10 most populated counties in Colorado."

I'm still yet to get a reasonable result from trying this.

I tried this a few times about a month ago. It sounded cool, and the experience of using it was even better than I expected.

I'm glad it was reposted so I get another chance at developing a habit of using it.

> That’s actually exactly how vegetarian buffets work.

I'm going to go out on a limb and guess you don't visit many restaurants that advertise vegetarian buffets

As a side note when in Brazil I felt like "vegetarian" food meant "just little bit of meat" and "caipirinha without sugar" meant "just don't mix (the layer of sugar at the bottom)" :) Did love it though.

Streamlit is awesome.

It's nicer than sending someone static results, and it isn't much more effort.

And vastly better than sending a notebook to someone unless you expect them to modify the notebook a lot.

And learning time to make Streamlit useful for a small internal apps is probably ~15 minutes for most people.

I can't emphasise enough what you put here:

> And learning time to make Streamlit useful for a small internal apps is probably ~15 minutes for most people.

For the types of things streamlit works for, it's minutes to learn and can be just minutes to write a useful app.

Yes. We use it for our own. We started however with a concept of AppBook[0] for the very "academic type" who couldn't even write a Streamlit app. We'd automatically take a notebook and parametrize it (no metadata or the user tagging cells), then present a form with the parameters. We'd then run it and track the experiment, and log the model.

Now, however, as some of our internal users are comfortable with writing Streamlit, we're directly deploying apps from the notebook. It's useful to show results to clients without the user having to set up a VM, upload stuff, Docker, authentication, resources, etc.

It's not really the 15 minutes it takes one individual to learn. It's the SSH into something, send a link, shut down the VM or recycle it for next proto, remember the IP, etc...

- [0]: https://iko.ai/docs/appbook/

This is really nice work.

If you had a mechanism to subscribe for future updates, I'd do it.

Either way, this is cool stuff.

Thanks :)

I've been trying to work out where to put updates, so far I've been using GitHub & Twitter (both @wagtaillabs). I'll keep posting to HN as well (I just had two orders of magnitude more traffic than any other day).

I'd be more than happy for any suggestions on places where people could follow (I've thought about an email list, but I'm not sure how many people actually read emails any more).

The author starts with

The data science world may reject me and my lack of both experience and a credential above a bachelors degree

More likely the data science world will reject him because he is so confident a field he has so little experience or knowledge of.

Data scientist is a profession rather than the name of an academic field. So data scientists' job is to solve practical problems. That involves a lot more than class assignments, and in some cases involves using machine learning to maximize predictive accuracy (because common ML models like gradient boosting capture interactions and non-linearities in a richer way than the GLM models the author is familiar with).

Their argument "that's a garbage model because we can't reasonably interpret underlying parameters," is replacing their personal criteria above what is needed to solve some problems.

They can blame it on only having bachelor's degree. But the real problem is the belief that a bachelor's degree taught them everything there is to know, and those in the DS field are ~ idiots who got lucky enough to be paid more.

I feel like the blog post should be read in line with how it was probably written: informal, personal and somewhat sarcastic, with a bitter note because he chose one major and now it turns out people value something else instead. Hence the title "the final stage of grief". I did not get the impression that the author thinks machine learning is stupid or that he knows everything about it.

If you send me an email (dan@kaggle.com) I'd love to set up a time to show you some mockups that may be the solution you are looking for.