Wesley Chuen

A lot of people claim to have models that can predict stock prices accurately, but I haven’t seen any that hold up under real market conditions. I recently came across a 2024 research paper reporting over 90% accuracy using an LSTM model on daily VN-30 index data. The setup included: • Indicators: SMA, MACD, RSI • 60-day sliding window • Four LSTM layers (30–60 units each) • ReLU activation, 0.1 dropout • 1,000 training epochs in TensorFlow and Keras The paper doesn’t say if that 90%+ figure came from the training set, test set, or true forward predictions. With only a few months of test data, that number might not hold up once market volatility kicks in. I’m planning to replicate the setup using daily data to see how it performs in real conditions. Will compare training and test accuracy against actual market prices. Should be an interesting little side project. Source: Nguyen et al. (2024), Humanities and Social Sciences Communications.

Picked up a pizza order. As I walked out, an elderly couple was getting out of their new Tesla Model Y. I said, “Beautiful car.” He said, “Thank you. It’s the best car I’ve ever owned.” I said, “Why?” He said, “You see me—I’m 78 and can barely walk, let alone drive. I’m taking my wife out for date night again after 52 years of marriage. We couldn’t do this with our old car. I didn’t buy this to save the planet. I bought it to save me.” 😢 All choked up, I said, “Thank you for sharing. You two go enjoy your dinner!” I see and hear this so often from elderly people buying Teslas, but it never gets old. Tesla is freedom🫶🏻

Almost every AI power user I know is MORE stressed and busier after using AI, not less What people thought AI would do: 10x productivity so that we can finish work earlier & relax more What it’s actually doing: 10x productivity so that we end up with 20x more things to do cos of the sheer possibilities

after this, I will shut up. just please: put yourself in the shoes of a customer that: - bought Model S/X in 2022/2023 (~$140k for a Plaid), or even 3/Y at ~$60-75k - paid an additional $15k for FSD (12 ½ years worth of subscription at current pricing) - doesn't have access to latest FSD versions because HW3 (missed cutoff point by a few months) - can't justify upgrading to HW4 because they’re deeply underwater on their current car - see $15k FSD purchase option drop by nearly half, even though Tesla said it was only going to get more expensive - see a great deal on a Cybertruck with "Free FSD Transfer for loyal customers!" advertised right below the Order button. press "Order." - aren’t chronically online, so miss Tesla quietly changing the terms retroactively - show up (or are about to show up) for delivery in June only to be told “sorry, we’re not honoring that” - then went online to figure out what happened… and got hit with “stop wanting things for free!” these customers exist, and will never buy another Tesla again.

@Loopify @Eli5defi works fine here as well. If they ban me, I'll switch to other providers, probably will cost less.

@Eli5defi didn’t they ban that and will suspend your account for that?

completely forgot they banned using subscriptions for this and you need api i hate anything api related such a waste anyone finding the solution to this? my current one is too small to run a big model any good small open source models?

@steipete @openclaw Ever since version 2026.2.12, all my full agents except the main one won’t response in discord channels anymore. I asked the main one to try to fix and nothing worked. Tried .2.13 and same thing. Had to downgrade it back to .2.9. I’m afraid to try the new versions now.

New @openclaw beta is up! This release is full of security hardening stuff so you really wanna get it. Ask your clanker to update to beta. github.com/openclaw/openc…

@unusual_whales Nice! Gotta try it out.

Building an agent with OpenClaw this weekend? Point it at unusualwhales.com/skill.md to level up your bot with real-time stock and option data from Unusual Whales. (Then reply to this tweet to show us what you're building!)

@jandatesla Yeah, it does that. We ended up in a ditch from our last ski trip. Never again.

Tesla Self-Driving generally does good in the heavy snow. In this particular spot FSD doesn’t slow around this tight curve and slides into the other lane. FSD attempts to correct, but fails by not slowing down. FSD told me to take over immediately. Kinda sucks it put us in a bad situation, and had me fix it. It’s like FSD said, “Oops, sorry. Good luck!” @elonmusk @aelluswamy @Tesla_AI

@_MG_ @lauriewired Reminded me to bring a solar USB charger with me. 😁

I thought I discovered a loophole in @lauriewired’s thought experiment. But the ability to simply provide the 5v needed to charge a phone hasn’t been possible for very long! Laurie suggested handing a smartphone to Bell Labs in the late 40’s would result in max gains for humanity. But what if the recipient didn’t have to rely on simply reverse engineer? What if it was a 2TB iPhone loaded up detailed info on all the critical research and tools that humans have discovered since then? Well, they are going to need to be able to charge the phone, else all that info is gone after the battery dies. Easy, especially for Bell Labs, right? Nope! It’s not about producing the physical connector of a USB cable. It’s about providing 5v at 500-1000mA that stays within 4.5-5.5v (and even that’s a very sloppy range). Not even Bell Labs or the military had the ability to do this in 1940’s, even though today you can buy a 5v wall charge for $5. It would be another decade until Bell could do this. And it was thanks to transistors which could regulate voltage output. Prior to then, it was world of high voltage tubes with huge voltage range tolerances. Low voltage DC with a precise range was doable, but only a few mA. I could imagine maybe stringing together a bunch of lead acid batteries, dropping the voltage with some resistors (maybe tubes?), buffering the output with capacitors, and having a person actively “riding” some trim pots to keep the voltage in the safe zone to offset voltage drift. I think Bell Labs could probably do this, and the 1940s were close to the limit for even them. What do you think? Using technology no earlier than 1945, how do you provide 5v at 1000mA that stays between 4.5-5.5v while a phone charges? Keep in mind, if you go beyond 5.5v, your magical smartphone from the future may be completely dead. How far back could we go just with this constraint?

@LeonXDreal @EliteDangerous Yes, I've stopped playing Elite dangerous for quite awhile now. What ship is this?

@wesleychuen @EliteDangerous You live under a rock don't you

Happy 11th anniversary to all of our Commanders! We'd love to hear your favourite moment from the past 11 years as well as how you'll be celebrating this weekend!

@AlejandroEV66 and taking up 2 spots of the charging space...

How-to: Using the official BMW NACS adapter 🤓

When I reported to Elon, we would have X product meetings at 5 or 6pm (because he was with the Tesla team for 10 hours before that), then my 1:1 checkin would be at 10pm, but that would regularly get moved to 11pm or midnight or 1am. Usually around 2am, he’d go take a nap for a couple hours in the office and then repeat the same schedule again the next day with a different set of companies, 7 days a week.

The first round of my AI stock prediction project wasn’t as accurate as I hoped, and it’ll take some time to refine and improve it. In the meantime, people have asked what else AI can do with the market. So I built a Tool Augmented Generation setup using OpenAI GPT with custom APIs that let the model access live data. It pulls technical indicators such as EMA, RSI, MACD, ATR, and volume, then combines them with company fundamentals like earnings growth, ROE, profit margins, and leverage. The model interprets both together to give an AI-driven view of a stock. The example below is GOOGL. *This is for information and experimentation only, not financial advice. #AI #MachineLearning #Finance #StockMarket

Applying AI to the stock market – Part 2: Reality check I spent the weekend replicating a 2024 deep learning model that claimed 90 %+ accuracy predicting stock prices using LSTM networks. The results were nowhere near that high. Training performance LSTM – Train 50.5 % / Test 50.4 % accuracy (essentially random guessing) Random Forest – Train 90.4 % / Test 89.1 % accuracy (for comparison) Confusion matrix results (Test set) Model Accuracy TP_up TN_down FP_up FN_down LSTM 50.36 % 48 21 33 35 Random Forest 89.05 % 71 51 3 12 I also built an automated hyperparameter tuner to optimize the learning rate, batch size, validation split, patience, recurrent dropout, and optimizer selection. Trying not to touch the other hyperparameters that the paper used yet. None of them moved the LSTM much above 50 %. Just like I originally thought, using AI and deep learning models looks convincing in papers, but I really have my doubts when applying them to a U.S. index like SPX that’s influenced by so many economic and sentiment-driven factors. I’ll keep refining the setup, including tuning the remaining hyperparameters and adding more engineered features, and see how much I can improve it.

A lot of people claim to have models that can predict stock prices accurately, but I haven’t seen any that hold up under real market conditions. I recently came across a 2024 research paper reporting over 90% accuracy using an LSTM model on daily VN-30 index data. The setup included: • Indicators: SMA, MACD, RSI • 60-day sliding window • Four LSTM layers (30–60 units each) • ReLU activation, 0.1 dropout • 1,000 training epochs in TensorFlow and Keras The paper doesn’t say if that 90%+ figure came from the training set, test set, or true forward predictions. With only a few months of test data, that number might not hold up once market volatility kicks in. I’m planning to replicate the setup using daily data to see how it performs in real conditions. Will compare training and test accuracy against actual market prices. Should be an interesting little side project. Source: Nguyen et al. (2024), Humanities and Social Sciences Communications.

@NVIDIAGeForceUK GeForce Day

🟢 GEFORCE DAY IS BACK 🟢 To celebrate, we're giving away TWO GeForce RTX 5080 Founders Edition GPUs, signed by NVIDIA CEO Jensen Huang. Want one? Comment "GeForce Day" for a chance to WIN & stay tuned for more!

if u work for @OpenAI be cautious about selling. --in the last several decades selling shares of market leaders with secular tailwinds has never been a good trade. --Sellers: Gates BAD. Jobs BAD. --Holders: Zuck, Musk, Ellison, Huang, Balmer GOOD. $AAPL $TSLA $MSFT $ORCL

Ugh! My Tesla Model X just got the 2025.32.6 software update, and it bricked my FSD and Autopilot! I tried holding the brake pedal and doing the two-button reboot. I also tried shutting the car down overnight. I even spoke with Tesla support, but nothing worked. The earliest service appointment I could get is October 3rd. I figured they could just push me another software update to fix it, but the support rep said he doesn’t have the power to do that. Once you have FSD/Autopilot, you can never go back! I have to borrow my daughter's model 3 to drive for now.

A Tesla owner left me this comment. Tesla is brining mobility back to the elderly!

I hope everyone realizes the mess Antifa is getting themselves into. They have TERR0RIZED Americans and ICE Agents for LONG ENOUGH! Here they are beating the life out of a Portland resident because he happened upon one of their protests. FAFO