Google Earth Engine's Foundation model via the ITU's seminar! This thing is incredible!

Anthropic has been doing this from the start and they are justified in it (the plan has different pricing rates than API). People have been making workarounds and they are justified in that as well - those people understand their workarounds are fragile when they made them.

While I agree a text representation is good for working with LLMs... most of the examples are mis-aligned?

Even the very first one (ASCII-Driven Development) which is just a list.

I guess this is a nitpick that could be disregarded as irrelevant since the basic structure is still communicated.

This seems a meaningless project as the system prompt of these models are changing often. I suppose you could then track it over time to view bias... Even then, what would your takeaways be?

Even then, this isn't even a good use case for an LLM... though admittedly many people use them in this way unknowingly.

edit: I suppose it's useful in that it's a similar to an "data inference attack" which tries to identify some characteristic present in the training data.

I think you mentioned it, when a large number of people outsource their thinking, relationship or personal issues and beliefs to chatgpt, it important that we are aware and don't because of how easy it is to get the LLMs to change their answers based on how leading your questions are due to their sycophancy. HN crowd mostly knows this but general public maybe not

I'm imagining a version of this where you have to use various prompt- or data-centric attacks to navigate scenarios

We want to gamify prompt hacking and give people an UI to add/remove chunks of the system prompt. It'll be unlocked by collecting widgets around the place.

I like to think of it as "maintaining fertile soil"

On android this is easy you can add a button to the bottom nav bar

Authors work seems awesome at first glance. Makes me want to learn erlang before learning elixir, or, at least, at the same time.

wow an actor OS?