AI on Cloudron
-
@LoudLemur said in AI on Cloudron:
@micmc said in AI on Cloudron:
Amazing resource to actually LEARN the art of communicating with artificial intelligence, a.k.a. prompt engineering
Interesting to know that some company are already looking to hire prompt engineers and I've seen salary offers of up to US$300k per year.
It's very well done and in several languages .
https://learnprompting.org/
Did I say it's totally free?Thank you!
Quick question: pre-prompt vs prompt?
I'm not too sure of what the quick question is but you seems to grasp the difference anyway
In fact, yes, before asking questions or "consulting" an AI agent, unless this last one is specialized, to get the best results you need to put the Agent in a situation (establishing an intention) so it does not get confused and 'knows' exactly on what to focus to establish the most accurate response as possible.
No need to say, the most precise is the prompt the most perfect in quality response you will get. You can imagine that some "pre-prompt" are much more elaborated than the examples you provide.
-
Here's an example of what can be done with "prompt engineering" knowledge.
https://prompthero.com/Fortunately, there already exist a huge amount of resources for less techy people to learn and access this technology.
-
@micmc said in AI on Cloudron:
Here's an example of what can be done with "prompt engineering" knowledge.
https://prompthero.com/Fortunately, there already exist a huge amount of resources for less techy people to learn and access this technology.
Thank you! You have helped me a lot and I am still trying to catch up on some of your suggestions. I feel like I am heading in a good direction though.
-
@LoudLemur said in AI on Cloudron:
Thank you! You have helped me a lot and I am still trying to catch up on some of your suggestions. I feel like I am heading in a good direction though.
You are very welcome mate!
-
ChatGPT 4 is now available to all fee-paying users. It remains proprietary AI.
https://openai.com/blog/gpt-4-api-general-availability
The Powers That Shouldn't Be don't want people to put "their" values into AI, or to raise doubts. DeepMind start pushing for 'regulation' over AI.
-
@LoudLemur The new Code Interpreter beta is WILD. Try uploading Wordpress plugins to it and ask how they work, and for it to create patches and add-ons. Amazing to see it in action!
Web Design https://www.evergreen.je
Development https://brandlight.org
Life https://marcusquinn.com -
-
-
@LoudLemur ChatGPT paid subscription, got to settings and enable.
-
- https://nat.dev gives you early access to GPT-4-32K for those that know the potentials that adds.
-
@marcusquinn said in AI on Cloudron:
Claude is good fun. You can tell it prefers to not give longer responses. Thanks for the link.
-
@marcusquinn said in AI on Cloudron:
GPT-4-32K
From you.com ai:
"what potentials are there for GPT-4-32K
Potential applications and capabilities of GPT-4-32K
GPT-4-32K, being one of the largest language models developed to date, holds great potential for a wide range of applications and capabilities. Here are some of its potential uses:- Improved natural language processing (NLP)
GPT-4-32K's massive size and scope can significantly improve the accuracy and efficiency of NLP applications, such as language translation, chatbots, and virtual assistants.
Its ability to contextualize information and draw connections between diverse topics can help overcome common NLP challenges, such as ambiguity, nuance, and complex sentence structures.
2. Enhanced problem-solving and decision makingGPT-4-32K has the potential to assist in complex problem-solving and decision-making tasks across various domains, such as medicine, finance, and engineering.
Its ability to generate coherent and relevant responses to open-ended questions can provide valuable insights and perspectives that human experts may overlook.
3. Advanced content creation and curationGPT-4-32K's ability to generate high-quality and engaging content can be used in various applications, such as writing news articles, creating product descriptions, and generating marketing copy.
Its powerful content curation capabilities can also be used to analyze and summarize large amounts of unstructured data, such as social media feeds and customer feedback.
4. Cutting-edge research and developmentGPT-4-32K's massive size and extensive training data can be used to push the boundaries of research and development in various fields, such as cognitive science, linguistics, and artificial intelligence.
Its ability to generate novel and creative ideas can also be used to explore new areas of research and innovation.
Overall, GPT-4-32K's potential is vast and varied, and it is likely to have a significant impact on the future of language processing and artificial intelligence." -
Elong announces his new AI company: xAI. It will tell us the truth...
https://x.ai/https://www.businessinsider.com/elon-musk-new-company-xai-website-2023-7
-
@LoudLemur The truth is, there is no single truth, just some superficial overlap. Otherwise, the truth is whatever you want it to be
-
@LoudLemur said in AI on Cloudron:
The Powers That Shouldn't Be don't want people to put "their" values into AI, or to raise doubts. DeepMind start pushing for 'regulation' over AI.
Ironically the title says : "We need humans at the top of food chain; says AI pioneer" BUT, startlingly enough that is actually a FACT!
It's also a paradox, because there wouldn't exist any AI technology without humans UP there, "at the top of food chain". It sounds bold, but that's very likely for making the headlines anyway...
Of course we understand that what he means is that it take humans to constantly be overlooking at AI apps and processes, so it's 'never' be left by itself, to maintain and enhance itself, and program itself even more powerful features by itself without any human supervision. (Yes, supervision is human, not AI's
)We already have "AI Surveillance Systems" over humans, but, indeed, we also MUST have to legislate, implement and enforce a "Human Surveillance over AI Systems" as well, and forever!
-
@marcusquinn said in AI on Cloudron:
@LoudLemur The new Code Interpreter beta is WILD. Try uploading Wordpress plugins to it and ask how they work, and for it to create patches and add-ons. Amazing to see it in action!
Can you IMAGINE man? And all this is only at the beginnings! We'll need to find another expression than "mind boggling"?
-
@LoudLemur said in AI on Cloudron:
Elong announces his new AI company: xAI. It will tell us the truth...
https://x.ai/
-
@micmc said in AI on Cloudron:
The new Code Interpreter beta is WILD. Try uploading Wordpress plugins to it and ask how they work, and for it to create patches and add-ons.
Under what licence does it release/create that code? For example, if I had it create a "Hello, world!" browser extension, what would the licence be, or is it just public domain?
-
@LoudLemur I believe their Ts & Cs say they don't claim copyright over output. With WordPress, it's typical that GPL is inherited. Otherwise, I'm sure it can be whatever you want it to be. Ultimately, the value in any code isn't the code itself, it's the usage and feedback on what the code does, and anything you publish open-source, that's then tried & tested, they'll then be re-ingesting to future LLMs. They're not interested in your license, they're interested in your proving code does what it says it does, as then it's valuable to re-ingest and increase their own code understanding and creation capabilities. You work for the robots now
