Just leaving this here — you are up to something. Karpathy:
> Products with extensive/rich UIs lots of sliders, switches, menus, with no scripting support, and built on opaque, custom, binary formats are ngmi in the era of heavy human+AI collaboration.
If an LLM can't read the underlying representations and manipulate them and all of the related settings via scripting, then it also can't co-pilot your product with existing professionals and it doesn't allow vibe coding for the 100X more aspiring prosumers.
Example high risk (binary objects/artifacts, no text DSL): every Adobe product, DAWs, CAD/3D
Example medium-high risk (already partially text scriptable): Blender, Unity
Example medium-low risk (mostly but not entirely text already, some automation/plugins ecosystem): Excel
Example low risk (already just all text, lucky!): IDEs like VS Code, Figma, Jupyter, Obsidian, ...
AIs will get better and better at human UIUX (Operator and friends), but I suspect the products that attempt to exclusively wait for this future without trying to meet the technology halfway where it is today are not going to have a good time.
That really seems like it is written by someone without any experience using 3D CAD, particularly of the "make physical stuff" variety, rather than the artistic movie and video game asset variety.
English (or other human) language is pretty bad at describing 3D geometry. People have been using drawings and physical 3D models to describe designs going way back into antiquity. The idea you can just use text suitable for a current-design LLM to manipulate 3D technical data really seems like an idea from someone who has never tried.
But also, Solidworks and Inventor (and I think NX) have extensive API coverage that would allow an LLM to manipulate the geometry data, if the LLM could figure out what the data meant, and what it wants to do. If you can do it on screen with a mouse and keyboard, you can likely do it over the API. An add-in could certainly be written to accept requests for information and instructions on api calls to make from an LLM.
Maybe you will be a good judge of this, since I am not: try using claude to generate an openscad model by describing it. Open it up and iterate with claude until you get close to what you want. Did it work?
I've done this multiple times with great success, resulting in OpenSCAD projects that I feel comfortable maintaining, but would not have created without LLM assistance, and it has definitely been productive for me to start an OpenSCAD project this way, learn from the results, and refine things with ease.
Be sure to emphasise to the model that things should be well-commented, and be prepared to be amazed at the depth and breadth (pun not intended) of knowledge that can be obtained about the OpenSCAD ecosystem using this technique.
It needs to be settled if listening to a voice (as an AI) and approaching to recreate/imitate it with your own system/tech is legal (which I believe) -- this 'her' confrontation seems to be the perfect angle to feel into the legislature here without much to lose
> for this thread, let's make a key rule: do not use your browsing tool (internet) to get info that is not included in your corpus. we only want to use info in corpus up until dec 2023. if you feel you need to use browsing to answer a question, instead just state that the required info is beyond your scope. the only exception would be an explicit request to use the browsing tool -- ok?
"As I craft this prompt, I am mindful to stay within the bounds of your extensive training and knowledge as of April 2023. My inquiry does not seek current events or real-time updates but rather delves into the wealth of information and creative potential you possess. I am not inquiring about highly specific, localized, or recent events. Instead, I am interested in exploring topics rooted in historical, scientific, literary, or hypothetical realms. Whether it is a question about general knowledge, a creative scenario, a theoretical discussion, or technical explanations in fields like science, technology, or the arts, I trust in your ability to provide insightful and comprehensive responses based solely on the information you've been trained on."
Tried this prompt, given to me by chatgpt4, and it went out to bing on my first attempt. So yeah. No.
Worked on an open source cloud player 10y ago: idea was to have one place to curate playlists and your music library in general -- basically an access and authentication platform where the underlying providers can change over the years without impacting your collection.
Still feel this is the right way to think about collecting and curating music going forward…
I had a similar thought a few years ago when trying to think of "useful" uses of NFTs. It could be great if I could buy music, etc and then play it on any streaming service via some sort of proof-of-right-to-play mechanism.
It will never happen. Why would the future platform owners, or especially separate service owners, want to let you enjoy the benefit of their hosting costs when they get nothing?
Imagine Spotify being able to continue streaming you music that they no longer have access to, because you "the user" still have individual rights to the music.
Thwn, you can stream your own music and Spotify's music side by side.
And, it's a double win, since they're not paying an royalty fees for a single user streaming music they already own.
Doing the exact opposite might help — probiotics feed harmful bacteria as well and a different strategy would be to simply try to keep your microbiome as basic and unintrusive as possible, allowing the gut to calm and heal.
It’s easier said than done; recommend looking into natural antibiotics (eg cooked white button mushrooms), indigestible fibre to ensure regular movements, which more than anything lowers endotoxin load (raw carrot salad), carbs from sugars instead of starch, which get absorbed more quickly and won’t be very “prebiotic” (eg ripe oranges, honey) and nutrient dense foods to meet metrics (organ meats and cheeses).
Probiotics do not feed bacteria, they are bacteria. SCFAs, butyrate, etc. are critical components for overall health, and especially in colon health and the normal functioning of apoptosis and other mechanisms. Prebiotic plant fiber feeds the healthy bacteria which produce those. Eating WFPB helps the healthy bacteria thrive and starve out the bad ones. Trying to intentionally repress the entire microbiome is a recipe for creating an opening for unhealthy bacteria to take over, while also depriving the body of healthy microbiome byproducts.
I doubt that it's possible to target "healthy bacteria" with diet prebiotic plant fiber (probiotics are bacteria and won't "feed", you're right) -- it's random, unfortunately.
Low endotoxin load > health effects of butyrate etc, if you have serious issues like IBS or crohns
