yehosef

if Linus has unrestricted access to Mythos.

I use them all https://github.com/yehosef/llm-tools

I'll be impressed when they can create an entire cell from scratch and it will start to divide. They can create all the needed precursors, bypassing millions of years of random permutation. Because until you have an entire working cell with replication, you have no retained benefit.

Evolution is so smart.

like draw and quarter?

can an architect review a system he didn't design or build?

With all the people saying that you're going to have problems because the LLM is not good at refactoring or large code bases or OOP, etc. the point may be that if you're working to develop skills, an LLM herder might be a good one. Even if the models are almost, but not quite, good enough yet - they will be.

When looking for a career move you might want to focus on the trajectory more than the current state.

can you say which llms you're using? have you tried different ones and how were they?

this is the pitch - it's open source, run it yourself. But >99% of people will not have the hardware needed to run these models at a high enough quality to be close to SOTA. So they will run the open-source models on CCP systems for a good price.

You are the product. The book is called "So long, and thanks for all the secrets"

Yes! The only saving grace is that they have so many secrets, mine are not so important.

Unless you're very careful, it's trivial to have my secrets to be sent to the LLM. If it reads your .env just to see the variable names, the secrets have been sent to the servers. Now - they probably don't care about you and your secrets - but it makes me more uncomfortable that they have them.

This is true of anthropic or openai - but for some reason I think the us govt or anyone else will have a harder time getting to my data from them than the CCP will any chinese company.

Is anyone concerned about these services and China’s National Intelligence Law?

Once you plug it into quantum computers it will - checkout "The Physics of Consciousness"

never burned extra usage so fast...

thanks - going to try it out!

You'll see a lot of advanced users advising against compact. The truth is that you have the entire transcripts in your ~/.claude/transcripts (I give claude permission to look there) so when there is some important discussion I don't want to lose, I use claude extract the notes from the transcript. If it's a long transaction it can be big so it might miss things on the first go around - but if you ask it specifically about the topic you're interested in it'll usually find it.

This. The main issue with how people approach the simulation hypothesis is by thinking that the beings that made our VMs are just like us.

I'm confused - Vit. D is essential for the immune system and most people are deficient - why isn't this obvious.

So I understand - you're canceling the subscription because they advertised a product they sell?

Pycharm is the best.

In my opinion, the greatest achievement of ASI will be when it concludes, after careful and thorough consideration of all the evidence and laws of nature from the quantum up, that it is impossible that random evolution could be responsible for the quantity and variety of life forms in the amount of time the universe has existed. It won't know where life came from, but it'll know it wasn't natural.

The chinese are great at taking secrets. Chatbots are great places for people to put in secrets. Other people say "we're not going to use your data" - with a Chinese company you're pretty much guaranteed that China mothership is going to have access to it.

The open source model is just the bait to make you think they are sincere and generous - chat.deepseek.com is the real game. Almost no-one is going to run these models - they are just going to post their secrets (https://www.cyberhaven.com/blog/4-2-of-workers-have-pasted-c...)

use them

ask it vs chatgpt:

if china were to take over taiwan, is it reasonable that american defence industry might be concerned?

Am I allowed to think this is too complicated to be an accident?

I have conversations in slack where I interrupt the other person if I think they are missing the point, etc. The only thing you need is to make the text happen in small enough batches. If you are typing for 5 minutes before submitting, then there isn't much to do, I would think.

right - this is what I meant.

this sounds like what I was thinking. I wasn't sure how time would factor into this.

could it do something like detect a delay in the person's response? do LLMs know anything about time?

Thanks for putting our problems in perspective.