So glad to see you have the tools now to turn your ideas into reality. I think this trend will completely revolutionize computer science. Please keep building.

where are you storing all these movies, are using some kind of CDN

i think the next decade is going to be very interesting, not just for computer science, but for business and other forms of engineering. i don’t think many people truly realize that these models/agents might make the entire concept of a workforce irrelevant, especially in technical fields. someone with a deeper understanding, who can be more specific with these models, might outcompete 100% of casual workers alone. people & companies are not ready for it.

it's the best model for coding & math stuff. nothing else even comes close!

this is a serious violation of people’s basic right to privacy. they’re using these spywares to monitor us 24/7, tracking our every activity. this future is unacceptable. nostr:note1e0ga8cf7cy78q0hqr3dzztrjz7hchtcug7cqnepd26k4e6kcnqrq5lserj

Google secretly installed this app on various Android devices without users’ permission. Reports suggest that it can scan through your photo gallery and takes up 2GB of storage. You might want to check your phones; you can just uninstall it from the Play Store: https://play.google.com/store/apps/details?id=com.google.android.safetycore

Typically, setting something like this up involves building your own RAG system, a database and powerful servers, essentially retraining the model. But with this massive 2 million token context window, my implementation skips all that. You essentially fine-tune the model by talking to it. This conversation can include text, media, PDFs, and instructions, you can upload all this data & instructions in bulk, & keep modifying it. Once the model acts the way you want and has the knowledge you need, you just save that state as a personality, it saves it locally. Then, the next time you open it, you start right where you left off. And you can reuse that state whenever you want, as many times as you want. This approach is much more accessible. Building and maintaining a RAG system isn't easy. Also, the model much more readily understands the context in this method compared to traditional RAG. The reason we don't use context more widely for model training is that we just haven't had enough context window. Only Google's modals has it at this scale, for now.

I really hope he finds the help he needs. I went through his feed, and it's really disturbing.

As much as I like Claude, it’s becoming increasingly clear that not only have they built one of the most heavily censored AIs, but they’re also developing censorship systems for other models. Its CEO has essentially become the poster boy for AI censorship. I really don’t want to support it anymore.

Gm, 🫡

Useful Nostr Tool: w3.do, Link shortener, it uses nostr relays. It works, I use it all the time. Build by a awesome dev nostr:nprofile1qqswlsm7jlayltt8neryk7npssqfklx8vpdvavx97445vnftnp4xpuqpr9mhxue69uhhyetvv9ujumn0wdmksetjv5hxxmmd9uzax4ze Link: https://w3.do