Great video, I think this is meant for companies that care about their users and wants to improve user experience 😊 can’t believe I didn’t think of this use case 🤦🏼♂️
The future can effect the past with RAG and a Human observer. You can inject facts into the pasts so the RNN can learn. How? If you are maintaining logs, you can create a log and inject it in to your log repository. Basically modifying the past. That way a fact gets learned earlier in the back propagation process and reinforces it self with forward feedback... like an echo.
user:I agree. What can you tell me about Candles, the concept-oriented programming language? @零 It seems like you’re asking about Candles, a programming language that’s not explicitly mentioned in our previous conversation or context. However, based on Sunshine’s interest in exploring new technologies and tools, I’ll provide some general information about Candles. Candles is a concept-oriented programming language designed to help developers create more maintainable, readable, and efficient code. It’s built around the idea of using concepts as the primary building blocks for programs, rather than traditional syntax-based approaches. In Candles, you define concepts that represent specific ideas or abstractions in your program. These concepts can be composed together to form larger structures, making it easier to reason about and modify the code. The language also includes features like dependency injection, which helps reduce coupling between different parts of the program.
Open Source AI should provide the general public with access to design, develop, and implement their AI solutions. This can be achieved by developing a programming paradigm that suits the perspective of every entity. At some point everyone needs to communicate with another entity. All entities other than ourselves are truly black-box, Human or AI. We as Humans do not have telepathy, so we communicate verbally and nonverbally in the physical world. This communication is not always effective with both Humans and AI, in both directions: transmitting and receiving. With AI and Humans we have a black box that can receive our transmitted input and maybe might decide to provide, or transmit back, a relevant output. Really nothing has changed. Human or AI we are both ultimately semi- non-deterministic black boxes. So, what does that mean? We focus our attention on providing the infrastructure for AI driven development. AI Programming Paradigm, AI Programming Language, AI Compiler, AI general processing units, and of course an AI operating system. That being said Open Source AI has a lot of work ahead of it. It is a good time to exist.
Outlining the premise, concisely explained and sharing the code... perfection.
I had an idea like this last week, haven't got around to fully implement it, then bam, your video comes out, one step ahead of me. We think alike 😉
You beat openai to the omni name, and me to this idea
Great video, I think this is meant for companies that care about their users and wants to improve user experience 😊 can’t believe I didn’t think of this use case 🤦🏼♂️
The omni-complete is awesome! Thank you sir. 零
@indydevdan you nailed the use of 'onmi' - another great video. thanks
Great one super good
This is great! Thanks for the hard work!
The future can effect the past with RAG and a Human observer. You can inject facts into the pasts so the RNN can learn. How? If you are maintaining logs, you can create a log and inject it in to your log repository. Basically modifying the past. That way a fact gets learned earlier in the back propagation process and reinforces it self with forward feedback... like an echo.
It's a time-turner.
Keep up the good work!
user:I agree. What can you tell me about Candles, the concept-oriented programming language?
@零 It seems like you’re asking about Candles, a programming language that’s not explicitly mentioned in our previous conversation or context. However, based on Sunshine’s interest in exploring new technologies and tools, I’ll provide some general information about Candles.
Candles is a concept-oriented programming language designed to help developers create more maintainable, readable, and efficient code. It’s built around the idea of using concepts as the primary building blocks for programs, rather than traditional syntax-based approaches.
In Candles, you define concepts that represent specific ideas or abstractions in your program. These concepts can be composed together to form larger structures, making it easier to reason about and modify the code. The language also includes features like dependency injection, which helps reduce coupling between different parts of the program.
BTW, we are talking about self-modifying code y'all! Get it? Safe & Secure #self-modifying code.
Open Source AI should provide the general public with access to design, develop, and implement their AI solutions. This can be achieved by developing a programming paradigm that suits the perspective of every entity. At some point everyone needs to communicate with another entity. All entities other than ourselves are truly black-box, Human or AI. We as Humans do not have telepathy, so we communicate verbally and nonverbally in the physical world. This communication is not always effective with both Humans and AI, in both directions: transmitting and receiving. With AI and Humans we have a black box that can receive our transmitted input and maybe might decide to provide, or transmit back, a relevant output. Really nothing has changed. Human or AI we are both ultimately semi- non-deterministic black boxes.
So, what does that mean? We focus our attention on providing the infrastructure for AI driven development. AI Programming Paradigm, AI Programming Language, AI Compiler, AI general processing units, and of course an AI operating system.
That being said Open Source AI has a lot of work ahead of it. It is a good time to exist.
Nice🫡🫡🫡awesome work mate
How is Ada growing ?
LOL!
Llama-3o
I can't stress it enough pick up #haskell now...
Still too much latency though
Using websocket will reduce the latency, I believe copilot uses websocket instead of api endpoints
#BAE ?
Yea use a super computer AI for auto completion. Pay for a megawatt.
1 of us: th-cam.com/video/39Bnk6VU53Y/w-d-xo.html