This is a really cool project. Love it. Why not extend to union, difference, and xor? Is that exercise left to the reader or is it not tractable? ;)

I'm also curious if you've consider fuzz testing this system to verify the results.

Good question!

One complication: For union the spec would look a little bit different than for intersection. I defined the solid associated to a mesh in a way that does not include the surface of the mesh itself. That works for the intersection. For union we would have:

solidWithSurface (meshUnion M₁ M₂) = solidWithSurface M₁ ∪ solidWithSurface M₂

I think it would not be hard to reduce the implementation and the proof of correctness to the intersection: There are some tricks which you can do like flipping the orientation of a mesh and putting a large cube that contains both meshes around it and then intersect these. (And then at the end doing the reverse trick.) Hopefully the implementation would not actually do this, but this construction could be used in the proof.

Regarding fuzzing. It cannot find the special cases I listed in the readme, because these cases are very rare.

Yet with formal verification we can prove that the implementation actually satisfies the specification for all of infinitely many possible inputs.

I extended weather history to 1 hour and added forecast for the next hour, too.

The data is available and I am considering it. Thanks for suggesting it!

No thanks!

An AI agent is not "conscious" without having skin in the game.

Another way of saying it, if an AI agent doesn't have true risk of oblivion (or mortality in the biological sense), it will not be incentivized to avoid it (or develop the ancillary processes associated with this avoidance ie desire to self-replicate).

What does that have to do with consciousness?

In my own experience, nano banana still has the tendency to:

- make massive, seemingly random edits to images - adjust image scale - make very fine grained but pervasive detail changes obvious in an image diff

For instance, I have found that nano-banana will sporadically add a (convincing) fireplace to a room or new garage behind a house. This happens even with explicit "ALL CAPS" instructions not to do so. This happens sporadically, even when the temperature is set to zero, and makes it impossible to build a reliable app.

Has anyone had a better experience?

The "ALL CAPS" part of your comment got me thinking. I imagine most llms understand subtle meanings of upper case text use depending on context. But, as I understand it, ALL CAPS text will tokenize differently than lower case text. Is that right? In that case, won't the upper case be harder to understand and follow for most models since it's less common in datasets?

There's more than enough ALL CAPS text in the corpus of the entire internet, and enough semantic context associated with it for it to be intended to be in the imperative voice.

Shouldn't all caps normalised to tokens like low caps? There are no separate tokens for all caps and low caps in Llama, or at least not in the past.

Looking at the tokenizer for the older Llama 2 model, the tokenizer has capital letters in it: https://huggingface.co/meta-llama/Llama-2-7b-hf

I work on the PixLab prompt based photo editor (https://editor.pixlab.io), and it follows exactly what you type with explicit CAPS.

The right answer for most people is to simply leave and pursue their ideals in a more favorable venue.

How could that more favorable venue be made, and have been made visible to him and to people like him?

The same thing has happened to me with political donations. Every day I receive an email from a different candidate. It is like whack a mole.

Great graphic on the environmental impacts of different kinds of grocery bags: https://ourworldindata.org/grapher/grocery-bag-environmental...

In short, single use plastic bags are very hard to beat.

Yes, but who wants to pay more for them? It's very hard to beat single use plastic bags for environmental impact: https://ourworldindata.org/grapher/grocery-bag-environmental...