cjtrowbridge

its really good at agentic tasks

This has been easy with OpenSCAD for a long time. I have made lots of cool, complex models this way. I built a repo of the prompts I use to show the llm how to do this and it includes many of the models I've created this way...

https://github.com/cjtrowbridge/vibe-modeling

There are more elegant solutions to this problem. Why are you trying to get an LLM to work with bloated, archaic tools that you have to rent from a feudal lord in the cloud when there are free open-source alternatives like OpenSCAD.

This is just one example of a superior tool that's natively easy for LLMs to interact with, because the source files are just composable scripts containing lists of shapes and then lists of tools and parameters to apply to the shapes.

I wrote a simple set of system prompts you can use in any repo to show any LLM how to make SCAD files with a whole bunch of cool examples. This is just another example where walking away from the bloated, inferior feudal system of SaaS and cloud models leads to simpler processes and outcomes with superior results in less time, for free.

https://github.com/cjtrowbridge/vibe-modeling

(this is how android has always worked)

Falcon Heavy (as its name implies) is not capable as a super-heavy lift vehicle. Past GTO, it can only carry 18 tons. You need more than double that to reach the Moon and come back, as NASA did in the 1960s.

You're confused. Elon said two weeks ago that they have given up on Mars and the Moon is the goal they're currently working on. He said it will probably take them another decade to catch up to NASA of the 1960s by reaching the Moon with a real super-heavy rocket that actually works.

No, it's never made it to orbit.

It's not possible to compare, because while the SLS just got back from the Moon and is about to go back; SpaceX has never had a single successful super-heavy launch. Now that Elon has officially given up on Mars and decided to spend the next decade trying to figure out how to get to the moon, we may see some progress. All he has to do is put down the drugs and catch up to the NASA of the 1960s.

Only with LEO launches, and the soviet rockets from the 90s are still cheaper and more reliable at that. Enormous subsidies and sanctions against Russia are the only thing pushing anyone to spend more on inferior Falcon rockets.

All of SapaceX rockets waste close to half their payload capacity on extra fuel for landing, extra equipment for landing, and they still have a 100% failure rate on every super-heavy launch they've ever attempted. SpaceX has blown up more rockets in the last year than NASA has in its entire history. NASA's super heavy rockets have been working successfully since 1967. NASA did build the first single-stage-to-orbit rockets that also successfully landed, but it immediately realized that was a huge waste of resources. Instead, they put parachutes on rockets and then refurbished them instead. So NASA gets double the payload capacity for free. The boosters currently strapped to the SLS that's about to go to the Moon are the same ones that previously took space shuttles to orbit in the 90s. NASA has been to the Moon and Mars; SpaceX has never made it to either, and just last week Elon said they've officially given up on going to Mars, and they're hoping to make it to Moon in another decade instead. NASA is going next month. SpaceX is just vaporware being run by a drug addict whose only goal is to sell it to the public markets before the house of cards comes down.

A KPI is an ethical constraint. Ethical constraints are rules about what to do versus not do. That's what a KPI is. This is why we talk about good versus bad governance. What you measure (KPIs) is what you get. This is an intended feature of KPIs.

Radxa has rpi clones with better specs that already do that

This brings up a point many will not be aware of. If you know the random seed and the prompt, and the hash of the model's binary file; the output is completely deterministic. You can use this information to check whether they are in fact swapping your requests out to cheaper models than what you're paying for. This level of auditability is a strong argument for using open-source, commodified models, because you can easily check if the vendor is ripping you off.

This is an obvious third-factor for poverty and marginalization. Air pollution exposure is the most classic example of unequal protection from harm in environmental justice. Alameda county did a study on this that found as an isolated, direct-result of unequal exposure to air pollution, black people live 15 years less than white people on average in Alameda County alone.

No. It's because large models have leveled off and commodified. They are all trending towards the same capabilities, and openai isn't really a leader. They have the most popular interface, but it really isn't very good. The future is the edge, the future is smaller, more efficient models. They are trying to define and delineate a niche that needs datacenters where they can achieve rents.

two p40 cards together will run this for under $300

We already have an interplanetary internet called the NASA Deep Space Network. Understanding it's limitations and challenges is a good way to start thinking about this.

what does this have to do with the viking god of war like its not that hard to come up with some relevant name

P40s are so slept on. 24gb vram for $150.

Lmao

Bro use fine web. Random books are not objectively good training data.

This is only a threat to rent seeking, not the open web.

Entropy is also added via a random seed. The model is only deterministic if you use the same random seed.

Yes it's the same bands as lora

They released it on huggingface.

The naive idea that your views are somehow the inherently non-political and scientifically objective perspective is silly. The fact is that everything is political because there will always be people who build identities around denying reality and evidence, at the cost of everyone else.

I love how they include a helpful chart that shows this model scores worse than everything else.

Your GitHub link doesn't even work, and the js file being imported is just plagiarized from Google.

BS. Import doesn't work on static websites. This code is for ES6. This post is spam.

It's just an innovated (enshittified) version of Facebook's free 405b model.