Andrew

Day Trading Software Engineer for @DailyProfilerCo
Giving retail traders access to quantitative trading tools

[Andrew @Tradesdontlie]

Claude controlling @tradingview live — switching symbols, writing Pine Script, batch scanning futures, replay trading, drawing levels. All from the terminal. Still rough edges but the vision is clear.

[Andrew @Tradesdontlie]

https://t.co/Ddl8b6fLX2

[Andrew @Tradesdontlie]

@DumbMoneyHunter how are you currently using it? is there anything you are interested in adding too it?

[Andrew @Tradesdontlie]

4500 stars on github guys this is amazing

https://t.co/N2AwCZ9Y9m

[Andrew @Tradesdontlie]

@Elmeromero88 allows you to connect your LLM like claude or GPT to tradingview desktop application

i use it to increase the speed of my indicator development

[Andrew @Tradesdontlie]

@DavidOndrej1 yeah but how many emails are hitting spam is the biggest question

[Andrew @Tradesdontlie]

@M6_USFTW @TradersConf https://t.co/N2AwCZ9Y9m

[Andrew @Tradesdontlie]

@traderkane just run /goal and it will just one shot it 99% of the time with enough context

[Andrew @Tradesdontlie]

every week there’s a new meta emerging with agentic engineering

[Carlos E. Perez @IntuitMachine]

https://t.co/CHEk211f7Y

[Andrew @Tradesdontlie]

@GPRTrades most people are just now building an indicator for the first time let alone building full data applications, python algos, or running randomized monte carlo permutation tests

[Andrew @Tradesdontlie]

if you use claude or chat gpt and build custom software you are in such a niche category and dine even realize it. (even more so for trading)

[Polymarket @Polymarket]

NEW: Just 2.2% of U.S. households currently pay for an AI subscription — PNC Bank.

[Andrew @Tradesdontlie]

99% of ICT traders have 0 data behind a system

even if your system is -> “CISD inside this window of time at X HTF array after taking previous session liquidity targeting opposing liquidity pool + other HTF array”

they don’t have the data behind it to prove it works across multiple/individual volatility regimes or daily classifications/ or how often this specific configuration of arrays even existed and proved success.

“price action was shit today” is different than “volatility is contracting so i should probably expect a smaller range and consolidation around the open today”

being discretionary is fine and simply trading any iFVG to a swing high after if taking a swing low is okay (i guess…) but if you’re really a psychopath with this shit yah might wanna trade with a data backed system not just blind faith. every hedge fund in the world trades with real data and so does ICT himself (he’s talked about the statistical significance of something plenty of times he just hasn’t shown you the histograms of it)

and to the people that think i’m crazy, you’re already trading with statistics you and don’t even know it. you trust a FVG or an OB because you have seen it so many times. you just don’t know the numbers behind to build a statical framework to prove its probability other than the times you have pressed the buy and sell button when it occurs in front of your eyes. believing in a pattern based system (model 2022) means you believe in its statistical significance. pattern based trading is statistical based trading without the numbers of its outcomes or distribution.

[Andrew @Tradesdontlie]

@Nek__12 so DAG but for agents got it

[Andrew @Tradesdontlie]

@HamelHusain this changed how i claude code

[Andrew @Tradesdontlie]

bro i’m tired stop changing the meta lol

[Peter Steinberger 🦞 @steipete]

Are we still talking loops or did we shift to graphs yet?

[Andrew @Tradesdontlie]

@Saboo_Shubham_ imagine the people who just learned what a git commit was today and this pops up on their time line lmfao

[Andrew @Tradesdontlie]

this completely changed how i claude code

[Hamel Husain @HamelHusain]

https://t.co/yk6wAhs0Zs

[Andrew @Tradesdontlie]

deciding the outcome you want, steer it in the right direction and if you don’t know the right direction ask it weigh pros and cons of a few different decisions and choose the best option that ALIGNS with your outcome

[Taelin @VictorTaelin]

I think I finally figured out how to use AI at scale

of course, the fact Fable is good is part of it. but I also changed how I work, and it all comes down to one key realization: you don't need to audit the code, but you NEED to audit the *choices* it made. if you just do that, things will work out, and you'll never lose a codebase to chaos. with Fable at least, the following seems to hold:

if I give it a good decision:
Fable implements it PERFECTLY

if I let it decide instead:
Fable may make some bad choices

that's how I see Fable: as a perfect execution machine capable of converting good decisions into good codebases, no matter how large. given a concrete plan, it lands its implementation. but when anything is underspecified, it can, and will, make bad choices. that's what you must audit.

"while working on this, which choices did you make that you're not confident of? list all."

then, you just review that. not the git diff, not 1000's of lines of code. just the choices it made along the way.

below is a fresh example. overnight, I asked Fable to fix an issue related to MatMul parallelizing worse than expected. it tracked the culprit with perfection, and landed a solution that DID work. but the solution was not general. it just doubled a buffer, which coincidently fixed the program at hands, but the underlying issue was still present.

when it completed the job, it declared success. if I just merged it blindly, the issue would still be dormant. that's the main mistake one can do with AI. instead, I asked it to spell out all decisions it made, spotted the bad one, corrected its course, and now the codebase is clean, correct and the issue is gone for good

I really think that if you do that religiously - i.e., NEVER merge without this "which decisions you made?" audit - you can go VERY far without ever reading a single line of code. at least on Bend, this is working incredibly well. despite heavy use of AI to implement an ungodly amount of features I could never dream of, the codebase is still in a superb state, with no signs of degradation

fresh example below ↓

[Andrew @Tradesdontlie]

@eptwts the fact my algorithm just feeds me Trading / SWE / Ai sauce is a blessing, sometimes i get movies or video games or random low IQ shit but for the most part its only tech

[Andrew @Tradesdontlie]

@realweirdgene that’s my dad!

[Andrew @Tradesdontlie]

you guys like my new cotton candy carnival chart colors or nah

[Andrew @Tradesdontlie]

@Solidrock85 @tradertheory i remember the first time i did the “math” on how to win the robbins cup and beat larry williams record just trying to scalp 10 points on nasdaq a day. fun times