Yeah I know, I am talking very fast + accent about cryptography, networking, consensus and other low level technical things, its normal to not get all of it.

Thing is if i would slow down and bring more context, the video would be 30m.

The video was meant to be like a commercial for the research paper.
Here everything is explained clearly and you can take your time.

https://1stbitcoinminer.com/

FWIW, if you would show this video to me 1 year ago, I would also not be able to follow.

Dude happy you like it.

Yup. They are all there.

The firs link is direct download to debug.log file.

Thanks.

I worked on this for 1 year continuously, thats why its good :D

https://www.paradigm.xyz/loom
What is this seems to be down.

Yes, soft pins is the easier way. In the mean time i vibed an extension for vscode, and indeed it's a mini todo list that i keep.

It's not the perfect as i still have to press cmd+c to add it in the list, but at least solves the problem.
But in this instance I manage this part and feed it to the model.

The annoying part is when I want to jump to that point in the chat, because i have to use cmd+f, so there is an extra step, but still works.

The only reason I cant remove these annoyances, is because of what the openAI/claude extensions expose.

Re point 1, seems to much work.

Also most people prefer to use the subscriptions not API.

Yup, it's LLMs 101, as it either collapses into the answer in a "straight path" or you force it to take multiple turns to get there and you go around the target instead of landing on it.

I need to start working on a personal stack for this. Thank you!

That's a nice setup, and I considered something similar, but I figured the time getting to work and debugging is not worth it, though the more time passes the better an investment seem to have been.

Man as you say this never argue with a bot, kinda makes me think I should re-evaluate the way I use LLMs.

Thing is that if 1st answer is not ok, chances are rest of convo will be hair pulling and force steering of model.

The model does forget(halucinate), because every time you send a new prompt the full conversation gets sent again, and as the context grows, it's not as good at remembring.

But that's not the problem, the problem is I want to reference certain thinks, like I want us to talk about the folder structure you propose for this thing, and i want to say this part is good, this is not good, this is also good.

Yes, it is veyr much a UX thing.

re: <subject of paragraph> - its not precise enough some times, when you reference it free form it allows more room for interpretation from the model.

Not trying to avoid question or be snarky, but i use it for everything.

My interactions with a agent start with a fairly big prompt from me and a big resonse from the agent.
This 1st reponse is the bulk of the stuff what we we go back and forth on.
So i want to have a very easy and fast way to reference things from this and other parts of the chat.

I found this to be the case for codings stuff, but also non-coding things.

I still am very involved in how I use agents and like to micro-manage hance why I do this often.

This is ofcourse more usefull in the planing/brainstorming/back and forth stages as thats where you want to reference things.

Btw since I wrote the OP, I already vibe coded somethign that works in vs-code will share later :)

To talk with the agent. What else could it be used for?

Got it.

The availability is indeed very novel, plus the availability and willingless of LLMs.

However this is not completely new. People have been outsourcing small task to asistants or other peopel that work for them for some time :)

LLMs are just an amplifier(at least for now) so you should use it to make your output 100x better/faster/bigger.

Allow LLMs to make you work harder on this you trully love, not to solve tasks you dont want.

So my diagnosis is that if you feel they are making you lazy you are not working on the right things.
(could be very wrong :P)

Agree, having a base is neccesary, i mean the LLM is like a very patient tuttor.

Same, though LLMs are good enough now that they can hold your hand if you want to learn how it works.

First time seeing this it looks like a lot of big block of text.

I was convienced by your post to make my way to the sub ~AGORA, but then in order for me to continue I need to take actions like scroll + click on a post and then back and so on.

Make my life easier not harder.

Minimise the nuber of steps, so that the only thing i need to do is scroll at most.

Also you should be more clear what is the advantage of using this vs. anything else in the world.

First sentance should convience me why this is the best thing in the world.

Make a static page and host it on github pages(its free) and have all the things to read in a more pleasant way)

This should be 1 prompt to any LLM.

Make sure to enforce good visual hiearchy. If you use claude code and the design skill provided by anthropic it will be exactly what you need.

Trust me 99.99% of people who end up here #942038 they say fuck it i won't read all of that.

You can also configure by using github actions (which are free) to check the SN posts and update the website, since i do understand the value is that everything happens here on SN.

Please do let me know what you think.