T-maps

Student of market - wanna be a GxT trader.

Ph. D. in Physics. - a researcher.

Daddy of two adorable kids.

[T-maps @labdorida]

@4xemperor GxT

[EasyWorld @sh740451]

카파시가 말한 LLM 위키
누가 제대로 구현해버렸다

이제 AI는 질문 답변 도구가 아니라
지식을 계속 쌓고 연결하는 시스템

소스만 넣으면 AI가 정리하고 연결하고 업데이트한다

핵심은 복리다
정보가 쌓일수록 가치가 기하급수로 커진다

기존 노트는 방치되지만
이건 AI가 유지보수한다

결국 방향은 하나
기록이 아니라
스스로 성장하는 지식 시스템

https://t.co/bAHzi651fh

[T-maps @labdorida]

@ICTtrader_KOR 이쪽은 이제 다...평정하고 넘어가셨습니까...

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[T-maps @labdorida]

@ICTtrader_KOR 진님도 음봉에 식겁한다.. 멤모...

[T-maps @labdorida]

공부하면 좋은내용!
a good material to study!

[ryan @_ryantrades]

mismanaged today

nonetheless, tons of lessons here

BE $YM

[T-maps @labdorida]

RTY long trade...
오늘은 주절 주절 쓰기는 아주아주 구찮아서 그냥 이미지만
이미지가 4개 밖에 안올라가서 그러는데
이 뒤에 Garret이랑 같은 포지션에서 YM long을 0.25r 정도 금액으로 잡았다가 손절나감...
*GxT를 paper trading으로 연습중인 기록입니다.

[T-maps @labdorida]

어제 수행했던 Trade recap입니다.
여전히 paper trading이고
GxT를 공부중입니다.
어젠 완전히 잘못된 Bias 덕에 좋은 움직임을 NQ에서 잡을 수 있었는데 다 보내줘야 했습니다. 혹시 lagging asset에서 잡아볼 수 있나 기다려보다 잡아 본 것이 잘된 경우입니다.

[T-maps @labdorida]

@dureup_J 저도 척추 휘어 있는데 어른도 이게 고쳐지나요?

[T-maps @labdorida]

I am trying to learn GxT
Of course, Yesterday, before the FOMC, I should not take the trade which ended up with Break even.
어쨋든 로직은 아래처럼... 짜보았긴했습니다.
반성하고 오늘 밤엔 더 잘해보겠습니다.

[T-maps @labdorida]

Practicing the GxT!!
GxTing!!!!!!!!
1 loss
1 win
total +1r

[T-maps @labdorida]

paper trading recap GxTing..
처음거는 뭔가 잘한거 같진 않습니다.
좀 chasing한 느낌 하지만
두번째꺼는 GxT universal sequence
15m 2stage psp 3m entry잘한거 같습니다.

[T-maps @labdorida]

trade recap입니다.
아직까지는 여전히 paper trading입니다.
GxT model을 연습하고 있습니다.

[T-maps @labdorida]

해외 trader들처럼 trade recap을 한번...
트레이딩 자체도 paper였고,
요것고 연습
GxTing...

[T-maps @labdorida]

@ICTtrader_KOR 차트를 보기만해도 제가 다 속뒤집어지는 무빙이네요 ㅎㅎ 코앞에서...

[T-maps @labdorida]

처음으로 올려보는 trade recap입니다.
이번에는 연습으로 성공한것만 업로드 하지만 다음에는 망한것도 올려보려고합니다. 망한거 올리고 that's the part of the game. 이라 하는것ㄷ도 간지나보이니까요.
뭔가 외국 애들처럼 피그마로 멋지게 만들어보는것도 장기적으로 해보고 싶읍니다.

[GxTradez @GxTradez]

The Model That Changed My Life Forever.

[ryan @_ryantrades]

my process in its simplest form

[T-maps @labdorida]

@escape_with_smc I will be your first student!!!

[T-maps @labdorida]

@y3fqx Guide