zerop

fine. Examples, what can I use this for?

Is it possible to generate code in LLM and create animation using Blender. I want to create Animation for educational video content.

Have you tried RAG on Open WebUI. How does it do in asking questions from source docs?

One big cost I can see right away is environmental issues and water shortages in areas where AI data centers would run. No one is bothering about it now.

Getting better models at the edge would help in this to some extent as it will decentralise the runtime of AI (still model training would happen in data centers)

Cobol is dead, really? Read comments and main article - "The code that controls our money" --

https://news.ycombinator.com/item?id=28458300

People have tried it on codebases, https://x.com/rseroter/status/1836519803802259732

One can do note taking with self on Whatsapp.

Quoting from whatsapp website (https://faq.whatsapp.com/5913398998672934)

> Use https://wa.me/<number> where the <number> is a full phone number in international format.

Put your own number and you chat with yourself. Pin it to top, so it's always there. I use it to add information, search later use cases.

AWS must provide ways to reduce the bill of customers.

From experience, if AWS can tell customers what computes/capacity is not fully utilised and can be shutdown, it will help. I am not sure if it does in some form.

Another thing would be customer definable cap on cost.

Another pain points - Need to keep a DR region active all the time, fearing Data center/AZ outage.

I had been using GPT4o for extracting insights from Scanned docs, it was doing fine. But very recently (since they launched new model - o1), it's not working. GPT4o is refusing to extract text from images and says it can't do it, though it was doing same thing with same prompts till last week. I am not sure if this is intentional downgrade and it can be clubbed with new model launch, but it's really frustrating for me. I cancelled my GPT4 premium and moved to claude. It works good.

Off topic: what's best way to generate good quality videos given a transcript. Only automation, no manual work. I can code.

Good stuff, like the AI approach to this.

On Jira, I keep hearing the criticism of Jira on this forum a lot, but IMO it's not that bad product. Jira is used by all industries, not just by software management. Making a tool has to be a "silver bullet" for managing any kind of project is not easy. Tell me a better PM tool which is as widely used as Jira.

Question - Do I compromise on quality on answers if I use models using WebLLM (like this) compare to using them on system console.

Can I use this tool to get toc for arxiv papers ?

Interested to know what is pdftomp3?

they should do streaming for voice inputs on the chatgpt app. right now it's very slow. Voice interfaces need to be streaming

> At Meta, we handle hundreds of trillions of AI model executions per day

Such a large number, makes sense?

Question - Can I use this to retrain an LLM (70B) weights on my own data? I am using RAG as of now for asking questions on my text, but always wonder if I could retrain an LLM on my own text. Thoughts?

Can I say - For RAG based system using LLM, will it be more effective to structure the source documents in this way?

Can this be run on Mac M1?

My method of learning new languages is always by starting to learn everyday conversations in the language.

1. Learn the translation of the commonly used everyday words

2. Learn the rule to build sentences in different tenses (Verb conjugation)

3. Keep practising in everyday conversations, starting with most simple ones and gradually learn more.

They should also add commenting capabilities under the paper.. a good discussion will lead to more research and information discovery

Such a useful information. If they published it no, I wonder why it wasn't there.

But why chrome implements CSS Animation in a way that would cost so much CPU?

Another OSS alternate - https://continue.dev/

Use cases for multi agents?

Context window is biggest limitation to LLMs, IMO. The great reasoning capabilities hit the context window limitation in many practical use cases.

Thanks. Is there any open source hosted solution like cursor that can use the Llama models ?

How to use this or gpt 4 for day to day code? I want to feed my code repo into it and generate/fix/explain code. Is the context windows size going to block me. Has anyone been doing it, with llama 2 models ?

Some things which are hard for someone might be easy for someone else. Usually academic things like calculus are seen as hard, but there are many hard things in day to day life, like selling anything to unwilling buyer, handling a rude customer with calm and much more. They too are hard and calculus guys can not do them well.

I will ask chatGPT to respond in "California Corporate" style, to know it more.