Viewing profile — braindead_in

Interestingly, all these things are required for loving kindness meditation practice as well.

Why not build a new browser with GPT baked in?

Does it respond in correct JSON?

I have been trying to figure out how to fine tune codellama. Will the llama2 examples work for codellama as well?

The universe is a infinite neural network and we are all weights and biases.

The 34b Python model is quite close to GPT4 on HumanEval pass@1. Small specialised models are catching up to GPT4 slowly. Why not train a 70b model though?

From a Nondualist perspective, our brain is highly complex biological neural network that has a special ability to reflect pure consciousness giving rise to the mind and the world …

The quote "The limits of my language mean the limits of my world" is attributed to Ludwig Wittgenstein, an Austrian-British philosopher. He expressed this idea in his work "Tractat…

Beautiful. Today is Masik Shivratri. I am planning to stay up all night, do some 5, listen to bhajans and meditate. It's gonna be magical.

What if something is different but nothing has changed in the model? Transformers are non deterministic. The response to same prompt may vary slightly, and can be controlled somewh…

I've played around with aider trying to run tests and fix the code, but it just crashes after exceeding the context window. I am now trying to repurpose the AutoGPT example in lang…

Cool project. I tried to build a reactjs Todo app with TDD, but it just put comments in the test file instead of the actual test. A self heal loop would be quite useful.

Count me in as well.

Can you recommend some good places in Rishikesh to experience all this?

> Those are the very people who should be never ever allowed to become mods, or to be anywhere near any position of power Okay. How about AI as the new mod then?

Someone please start the GPT 5 training before the regulation kicks in.

> With these updates, we’ll be inviting many more people from the waitlist to try GPT-4 over the coming weeks, with the intent to remove the waitlist entirely with this model. Than…

It's so mind-boggling to think that our everyday reality can be encoded as weights and biases in a giant matrix. Maybe we are just weights and biases.

> OpenAI and others have proposed that licenses would be required only for the most powerful models, above a certain training compute threshold. Perhaps that is more feasible Someb…

Aider looks cool. Gonna try it out today. Have you tried out StarCoder or Replit-code?

I mostly agree with the piece, except this part. > And AI is a machine – is not going to come alive any more than your toaster will. There have been claims that AIs are conscious. …

> The idea of inner monologue is to instruct the model to put parts of the output that are meant to be hidden from the user into a structured format that makes parsing them easy. T…

What about the roadmap itself? Can we look forward to these goodies?

What about the plans itself though? I was looking forward to faster GPT-4, 1M context length and fine tuning APIs. These won't be coming anymore? Feel sorry for the Humanloop guys …

I am looking forward to faster GPT-4, larger context windows and finetuning APIs. The combination of these can solve most of problems that I currently face with my LLM apps. It loo…