ALGO TRADING x AI

@PeterLBrandt The complexity usually signals uncertainty. Traders who know what they’re looking for don’t need ten screens to find it.

When it comes to trading, I am all into compactness and simplicity. All these multi screen big office operations are for the “show.” Simplicity is for the “go.” Totally not impressed with the 10 screen layout.

@zarazhangrui Multiple Claude Code sessions running at once is genuinely hard to manage. The fix I landed on was treating each session like a separate build with a defined output before opening the next one. Scope creep across sessions is where the delirium comes from.

My single biggest pain point right now: AI-induced attention deficit I have 5 Claude Code sessions running 10 Terminal tabs open 50 browser tabs open 100 X articles in my bookmarks When there are multiple AIs working for you, you're constantly task switching When you're waiting for AI to output, you're constantly distracted Because what used to be hard is now so easy, you always wanna do more, more, more Because of the speed of the AI news cycle, you feel a constant need to be on this app Add all this up and the result: you live in a constant state of distraction & delirium. Focus & deep work is harder than ever If anyone has figured this out pls teach me how

@karpathy Same bottleneck exists in bot building. The trading logic is rarely the hard part. Connecting execution, data feeds, error handling, logging, all of it into something that runs reliably without you touching it. That assembly is where most people get stuck.

When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!

@TradersConf $23k on courses is a lot of money spent on other people’s edges. The only system that works long term is one built around your own observations.

I've spent $23,000 on trading courses and have only lose money from trading. I hate this game.

You don't have to be a good trader before you start building bots. Learn both at the same time. The tools are there now. Try things, break things, keep going. Waiting until you feel ready is how you never start.

Hallucination isn't Claude making mistakes. It's you leaving gaps. Leave out your ATR multiplier, it fills one in. Leave out your fee model, it assumes zero. The output looks confident because the model has no way to tell you it made something up.

Your prompt isn't a question. It's the starting conditions for the output. Same model, same capability, completely different result based on what you put in. People blame the AI when they should be looking at what they fed it. Change the input, output changes. Every time.

@TraderDiegoX The bot doesn’t hold any of those beliefs. That’s not discipline, it’s just how code works. The hard part is building a system you trust enough to let run.

Revenge trading is not an emotional control problem. It's a belief problem: - You think losses are bad - You think stop losses mean the system failed - Your self-esteem is tied to trade results - You believe the market can be controlled - You don't understand that stop losses carry edge Fix those. Revenge trading disappears. No willpower required.

@AtifHussainOG The accumulation phase looks identical to spinning your wheels from the inside. Only the data tells you the difference, and only if you’ve been tracking it properly.

You'll backtest for months and see nothing change. You'll journal for weeks and feel like it's pointless. Then one quarter, the compounding kicks in. You'll make more in 3 months than the entire previous year. Invisible, then undeniable. Stay in the accumulation phase. The explosion follows.

Will manual traders still have an edge over bots? Some of them. But those people are rare. Always were. The ones who can actually sit there, execute perfectly, no emotion, every session. That's a tiny percentage and it always has been. Most of us aren't that person. Better to know it early.

@jtrader Automate the rules and the discipline problem disappears. The strategy runs the same way every time regardless of what you’re feeling.

Trading isn't hard because of the charts. It's hard because you keep breaking your own rules. The strategy works. Your discipline doesn't.

@1MINUTETIP Your edge has to come from your own observations. Borrowed conviction doesn’t survive a drawdown.

You are never going to be the best version of yourself trying to be like somebody else. Trying to be another trader will cost you. The market exposes that fast.

@samuraipips358 Most traders are in live markets trying to find their edge instead of verifying it first. The preparation isn’t optional, it’s where the trading actually happens.

What if you were the best trader? A red day would probably no longer carry any meaning at all. And when you see a trader who assigns some special meaning or emotional weight to a losing day, what would you, as the best trader, think? What a "trader" truly does is nothing more than a process of preparing a system with an edge in advance through a large sample size, and then continuing to repeat consistent actions afterward, "continuing to generate every win and every loss." A trader who can fully embody this from the preparation stage is exceptional. What task do you need right now? Think backward from the best trader. In most cases, it should lead you to "preparation." Do not jump into live trading unprepared just because "you want to make money quickly," and try to invent a strategy through the wins and losses in front of you. Prepare properly, and be consistent.

@tradermike1234 Targets belong where the price action supports them, not where the ratio looks clean. Forcing a 1:3 on a setup that only gives 1:1 usually means watching it reverse before hitting target.

One of the dumbest things you can do is force your rr on the chart (which is what many big rr traders do) "I need my 1:2 so I will extend my target here randomly" No silly Play the price action not your rr And you know what you will find? 1:1 is available alot more Shoot for more than that....you struggle in most conditions NOT ALL...but most And by the time the market meets the conditions where your play will run your psychology is already destroyed

@TradingComposur You can’t stay in the game long enough to get good if you can’t take losses cleanly. Winning comes later. Losing well comes first.

When it comes to trading, it can be argued that learning to lose is more crucial than learning to win.

@juandoo__ The filtering is the point. Most people find out early that they can’t handle the uncertainty. The ones who stay long enough eventually stop needing it to feel certain.

you can’t be a bitch if you wanna become a profitable trader and that’s exactly why this game filters people you’re gonna get smoked question yourself have people around you think you’re wasting your time and still need to wake up sit down and do it again no guarantees no certainty just you vs your own mind it takes obsession it takes delusion it takes ignoring odds stacked against you most people quit the ones who don’t take everything

@jtrader The bot executes the plan exactly as written every time. That consistency is the whole edge.

The market doesn't reward intelligence It rewards discipline You can have the best strategy in the world, but without execution, you're just another gambler with a dream. Stop chasing setups and start following your plan.

@TradersConf Geographic freedom is one of the most underrated advantages in trading. Lower fixed costs means less income pressure per trade, which changes every decision you make.

I live in Chiang Mai and my monthly expenses are $1,600. I make $5-10k from trading. My rent is less than what I used to spend on food in New York.

@samuraipips358 Automation routes around the whole question. The code doesn’t hold beliefs about money so none of the emotional chain gets triggered in the first place.

Many people blame the emotional problems in trading on the reptilian brain or frame them as a nervous system issue, and claims such as "It is impossible to remove fear from trading" are common, but that is completely wrong in trading. The reason is simple. The emotions that arise in trading are fundamentally different from primary emotions such as feeling fear when hearing a loud sound like thunder or feeling fear in the dark. A baby does not cry or feel afraid when looking at a chart because it has no idea what it is looking at, and a reptile does not look at a chart and perceive a threat to its survival. It is nothing more than pixels on a screen. In order to feel fear or excitement in trading, understanding is always a prerequisite. These emotions arise precisely because you hold the belief that losing money is bad and making money is good. We are not reptiles. That is exactly why understanding and perception matter, and why preparation to redefine trading is so important. Many people view the mechanism of emotion as "stimulus → response" and think that getting angry after a loss is only natural, but in trading, the correct sequence is "stimulus → perception → thought → response," so if your perception and thinking change, your current emotional problems will change completely. And those are tied to how you understand trading and to the depth of that understanding. That is why, when it comes to emotional issues, I always say not to look at the emotion itself, but at the thinking behind it. A true trader is not afraid to begin with, nor are they controlling their emotions through sheer mental toughness. Just because you have not solved that problem yet does not give you the right to decide on your own that "it is impossible." Fear is no longer part of my trading.

@iamdisplacement The edge is built through the process of finding it, not the result. That’s why copying someone else’s system never works the same way.

You'll study 50 different traders. Download their indicators. Copy their settings. Mirror their timeframes. And lose with ALL of them. Because their edge was built through THEIR screen time. THEIR losses. THEIR thousands of hours. You can't download experience. Build your own edge.