cloudking

Live demo 404s

What is the link?

This is why I'm not understanding the excitement around open source models, they pale in comparison to GPT-4 quality, so I have no use for them until we have something comparable.

Is anyone using open source models to actually get work done or solving problems in their software architecture? So far I haven't found anything near the quality of GPT-4.

Updated comment with examples

There are so many generative AI tools for creating game assets now, you don't really need to become a good artist.

https://www.scenario.com/

https://www.rosebud.ai/ai-game-assets

https://www.layer.ai/

Coming soon https://unity.com/products/muse

He spoke on Bloomberg too https://www.bloomberg.com/news/videos/2023-11-20/microsoft-w...

Would be great to have a local home assistant voice interface with this + llama + whisper.

It wasn't working until I went to settings and cleared/updated the filter cache, now seems to work again

Well it says he was not fired due to malfeasance, implying he had no wrongdoing.

It's great for keeping up with tech news. I wish it were a bit easier to follow and keep up witb conversation threads, especially on big news items.

Purely speculating, but could there be some sort of 4D chess move going on here? Look at the timeline:

1) The board puts out a press release saying Sam was outed for not being candid

2) Internally a memo from the COO circulates saying that is not true

3) Greg and other senior folks quit

4) Now he is in a negotiating position to return for a) being fired on a false premise and b) bringing back all the top talent

If someone wanted to restructure the board of this company, they could have fed the other board members false information to put Sam in this negotiating position. It's also strange that a bunch of billionaires voiced support for Sam immediately after the firing without knowing any details.

Confirmation https://twitter.com/gdb/status/1725667410387378559

I copy and paste chunks for small changes, or ask for fully updated code and copy the whole thing if there are complex changes. Your project sounds very interesting! I'll give it a try, thank you

I've found expanding conversations with GPT-4 are most effective for building code snippets. Start with asking for the basic functionality and continue expanding the feature set. Here's an example of building a simple local frontend app to interface with the TTS API https://chat.openai.com/share/8ea1e3ea-0763-4118-8c83-a2f5ea...

On a high level assuming the concept of an AGI is even possible, I think AGI would be a system that creates ideas and makes decisions on it's own without being "instructed" what to do like the LLMs we are seeing today.

Thanks for sharing, this is interesting. I'm curious how scraping a website for a GPT knowledge file makes the GPT "better" than the standard model? Can it not answer the same questions, assuming these pages were already part of the training of the standard model, or by leveraging the browsing feature to extract the same knowledge on the fly?

What engine and web stack did you use? Curious about how you built it!

You're welcome! Please share examples of how it's helped

Really any similar meta prompt will work, the key is you're getting the LLM to give you an optimized prompt. Try getting creative with how you ask for the optimized prompt.

Definitely upgrade to GPT-4, night and day difference in quality.

You'll get a different response each time, but the point is to now give it your goals as described for the prompt you want, it will give you back an optimized prompt you can start a new conversation with.

The most effective way I've found to prompt GPT-4 is to ask it to create the optimal prompt for you. Try this meta prompt to help craft your prompts:

--

I create separate conversation threads for each expert persona of GPT. You are PromptGPT. You are a prompt engineer expert for large language models. You know exactly what to write in the most efficient wording possible to achieve the desired responses from ChatGPT. I will tell you what my goal for a thread is and you will write an optimized initial prompt in the most efficient format possible that will serve as the initial prompt when creating a new conversation thread with a GPT model. You will define the expert persona, the parameters or rules of the responses, you should also provide any other information that a GPT thread may need to understand exactly what it needs to do to give me the most accurate answers depending on my goal with that particular thread and the tone of voice, within the prompt you provide.

Are you ready or is there any other information you need to perform this job to your best ability

--

Fun little game! Nice work

Firebase has a free tier with 10 SMS messages per day. Can use their API to send the messages. https://firebase.google.com/docs/auth/limits

Are you passing the entire context of the page code to the LLM to get back the XPath?

Neat! Can you describe how the integration works and what APIs you implemented?

I think I need to be in the higher usage tier to unlock the full 128k context length

Has anyone been able to access the 128k context window? I'm not seeing that option in the API playground