Hey! While I was similar to your child (now a good few years older), I'm not a parent or really knowledgeable in these situations, but I'd highly recommend checking out Dr. K ("Healthy Gamer").
I made a small web app with it that uses it to remove backgrounds from images (with BRIA AI's RMBG1.4 model) at https://aether.nco.dev
The fact you don't need to send your data to an API and this runs even on smartphones is really cool. I foresee lots of projects using this in the future, be it small vision, language or other utility models (depth estimation, background removal, etc), looks like a bright future for the web!
I'm already working on my next project, and it'll definitely use transformers.js again!
If I'm not mistaken, this is not on the models itself, but rather on the implementation of the addon.
I haven't found an open source VSCode or WebStorm addon yet that allows me to use a local model and implements code completion and commands as good as GitHub Copilot.
They either miss a chat feature and/or inline action / code completion and/or fill-in-the-middle models. And if they do, they don't provide the context as intelligently (? an assumption!) as GH's Copilot does.
One alternative I liked was Supermaven: It's really really fast and has a huge context window, so it knows almost your whole project. That was nice! But - one thing I ultimately didn't continue using it for: It doesn't support chat and/or inline commands (CTRL+I on VSCode's GH Copilot).
I feel like a really good Copilot alternative is definitely a still missing.
But: Regarding your question, I think GitHub Copilot's VSCode extension is the best - as of now. The WebStorm extension is sadly not as good, it misses the "inline command" function which IMHO is a must.
I'm not making this up, I thought the same almost immediately and only then saw the throwaway's message: By the first paragraph, my spidey senses were tingling, and by the first two sentences of the second paragraph, I wanted to write the same... and then saw someone already did.
I hope you do have the ability to get it assessed eventually. If you do, make sure to go to an adult(!) ADHD specialist (psychiatrist/neurologist) not a regular psych.
In the meantime, when you read about productivity tips, try reading about ADHD-specific productivity and organization tips, I think they might help a bit better.
I used a Growkit with no experience at all; and it worked beautifully. YMMV.
The yield is "not as big", right, but it's still more than you can reasonably consume. I don't quite remember, but I think three flushes yielded ~50g (dry) or so out of one small Growkit. Two big glass jars full.
I want to do it again out of enjoyment for the grow process alone. It's really fun watching these things grow!
I also read into vitamins and minerals (while trying to ignore all the snake oil), and I agree with you!
I tried a lot and the ones I keep buying are the same you do - Magnesium, Omega-3, D3+K2 and a B complex. These are not only the ones that most people are likely to be deficient in, these were also the ones that I subjectively felt had a positive effect on me, and either low or deficient levels were confirmed by blood tests. I feel a lot better, too! :)
Regarding the magnesium: I did not know that. How do you make sure the brand and/or it's magnesium is of good quality?
It's curious you say this, I wasn't totally sure, but I sometimes felt like there was a difference in quality, even between the same brand or product of the same form of Magnesium.
I agree, the README is not really understandable if you're not into AI research techno-babble. Just adding one sentence targeted at normal people would maybe have been useful.
To answer your question, it's a model that you can give image and videos, which you can then interact with via an LLM (ask questions, describe, process further, etc.) It can "see" them, basically.
It the same capability as GPT-4V (ChatGPT's "upload image" feature), except that ChatGPT only offers images.
Why? Just observe how art and content is perceived before and after you tell people it was made by AI. I think it's an unfounded bias.
You probably remember the AI art piece that won an art contest? It was perceived as better than the rest, obviously, or it wouldn't have won - until it was revealed it was made by AI.
Now, IMHO, that was not fair and if it was disqualified, that was absolutely the right move, but that's not the point.
The same can be observed when people talk about (AI) art. I've seen people comment "Awesome! There is just something about [this artwork] that AI can't reproduce, human art has soul!" even though the artwork they commented on* was made by AI
After it is revealed to be AI made, it is suddenly "soulless" and not genuine anymore.
I remember there was an online mental health care platform that (without revealing this) introduced AI therapists. According to their analytics, the AI therapists, on average, got higher scores than the human therapists. Then, word got out they're using AI and suddenly, people rated the service a lot worse than before. It was obviously wrong to not disclose this.
There's nothing wrong with valuing craftsmanship and human work higher than machine work. We as humans do and I do, too - but generally, nowadays, digital watercolor art made in Photoshop (and co) is not inherently considered "not creative" or "soulless" because it wasn't painted with real watercolor... but I'm pretty sure that was not always the case. I'm sure artists discussed about how digital art is not genuine, creative or soulless back then, too.
Can anyone that was there at the time tell me if there were similarities in sentiment when digital art and Photoshop (and co) became popular?
What I'm trying to say is that there is definitely a bias at work and people generally can't tell the difference if they are not told about the (possibility of) involvement of AI.
I also fear that currently, we're just the lame adults that don't like the new thing and eventually in 10 to 20 years after AI art is normal and accepted by the generation that grew up with it, something new will come out that that generation will think is lame and not genuine, and so on.
That is how I remember it. I'm relatively sure, but take it with a grain of salt - memories are, as we know, not reliable.
I'm not an ML engineer, just interested in the space - but as a general ballpark, training these models from scratch needs hundreds to thousands of GPUs.
There is a podcast episode of Lex Fridman talking with Mark Zuckerberg, and in this episode Mark states that the reason Llama is (and will stay) open source is that that is the deal that Meta has with the engineers.
To get top engineers, there had to be some agreement, and this agreement apparently is that the engineers want their work open sourced.
... and saw that at least this page containing information regarding an USAID grant is now 404ing.
Look at this:
https://foreignaffairs.house.gov/wp-content/uploads/2023/08/...
It is a letter from republicans about the USAID grant some report to be "for spreading atheism in ethiopia" (it's not).
They quote this link in the footnotes:
https://www.state.gov/statements-of-interest-requests-for-pr...
This now leads to a 404.