@nequalonetrader This is sorta useless without knowing more information on the size and strategy. Looks very normal at first glance if small
English
Hackworth
570 posts
Hackworth
@HackworthAI
Building quantitative AI systems Research @ Tensor Investment I trade crypto, fixed income, commodity, & ETFs Advisor & Builder @ AlphaNet
Hong Kong Katılım Mayıs 2025
146 Takip Edilen629 Takipçiler
I legitimately dont know of any fund that has been this consistent since Madoff. Not even MLP can match this. Straight up fraud probs.
English
What if all the small-cap data you actually use was finally organized in one single app? 😁
English
True, so Almgren-Chriss is severely outdated as it mainly has market impact and variance risk as a quadratic or stochastic control algo. Robust price prediction (or alphas if you will) can deliver the bulk of execution performance.
That's why in recent years DRL (deep reinforcement learning) based algos have a measurable edge against the likes of AC.
English
A large part of the answer to “what is an execution algorithm” is not stealthy iceberg orders and sneaky flow hiding, it’s just having great short term alphas you use to inform whether to execute faster or slower.
0xDipper@Dipper_pol
This is the rarest piece of HFT content on the internet - Robert Almgren walking through a real execution trade tick by tick He's the co-founder of Quantitative Brokers and the man who wrote the Almgren-Chriss model - the standard execution algorithm used at Goldman, Citadel, Two Sigma In this lecture he shows a live order from May 14 2018, every fill, every limit, every market reaction across 2 minutes and 40 seconds The article above is that exact same thinking applied to Polymarket - measure your edge in bits before you place a single trade Bookmark it & give it a watch tonight ↓
English
@FixedIncQuant Almgren Chriss is visionary but more or less outdated at this point. DRL (deep reinforcement learning) algos have outperformed quadratic and stochastic control methods in recent years by a large margin
English
I was a fly on the wall when Noel Chriss first described this problem to Rob Almgren. I was an intern at Morgan Stanley (in Chicago) working for Niel. he would periodically come down to meet with us & took us along in his meetings with other UChicago faculty/PhD types.
0xDipper@Dipper_pol
This is the rarest piece of HFT content on the internet - Robert Almgren walking through a real execution trade tick by tick He's the co-founder of Quantitative Brokers and the man who wrote the Almgren-Chriss model - the standard execution algorithm used at Goldman, Citadel, Two Sigma In this lecture he shows a live order from May 14 2018, every fill, every limit, every market reaction across 2 minutes and 40 seconds The article above is that exact same thinking applied to Polymarket - measure your edge in bits before you place a single trade Bookmark it & give it a watch tonight ↓
English
@quantbeckman Add explainability to the mix and one will be less worried about this
English
Rationalization and trading… everything is very logical, very beautiful, and very coherent… until that spike catches you, that Trump tweet, that unexpected turn, that early session close, that “I clicked the wrong button,” that hunted stop, that…
English
@quantbeckman less efficient, less tested, and less robust then just a deep learning return prediction layer + differentiable portfolio optimizer layer enabling end-to-end training + optimization
English
The paper is pretty ambitious, it tries to connect causality, no-arbitrage pricing, filtering, PDE control, manifold geometry, and empirical portfolio performance in one framework. You can imagine how many pitfalls it has...
English
OK so I claim credit for this paper 😄 (whitepaper actually). Deep learning denial/hating in quant industry is real, but Chinese shops have just embraced it heavily, from mid 2010s. You will see Chinese shops delivering rentech-like returns on US equity markets within the next year or so, mark my words.
AlphaNet@AlphaNet_AI
Traditional quant strategies utilize "alpha mining", utilizing often explainable signals (price/volume, microstructure, macro, event-driven etc) to generate trades and positions - and this is what majority of Wall Street firms use. In China over 80% of the top quant firms heavily utilize deep learning systems (including Deepseek's parent High Flyer), a black-box approach that is often non-explainable and uses deep neural network based trained on years of historical data to output predictions from hundreds or thousands of data points. It is a controversial topic, which practitioners in category often critiquing the other. This 47-page paper compares in detail both approaches and provides an argument on why deep learning has bigger long-term moat. It also covers frontier approaches for portfolio management in deep learning strategies. (Hint: multi-asset portfolio strategies coming to AlphaNet) The paper is first being published first in the Chinese quant and academic industry - source is below: alphanet.global/Alpha%20Mining…
English
I'm his neighbor in Shanghai and deep in the quant circle in China so I can say a thing or two about this.
High Flyer's prop is around a few $B in size. They are a top 3 quant fund with AUM north of $30B (exact undisclosed but could be up to 50B). Between the founders theyve accrued a lot of cash across the years.
He is likely worth north of $2B liquid, possibly 3, so the capital injection would definitely involve loans, which he can easily get at this point, financed by Deepseek private shares and high flyer cash flows.
English
tech ppl are so stupid when it comes to finance
they hear 'hedge fund' and eyes glaze over with dollar signs
Liang doesn't have $3bn liquid, must be borrowing from banks (aka gov) to do this
you can't make $3bn liquid on a $10bn fund, even at 2/20
x.com/cryptopunk7213…
Ejaaz@cryptopunk7213
deepseek is raising a monster $7 billion round at $50B val making it china's largest ever AI raise but what shocks me the most is the founder, liang wenfeng: > he's personally contributing 40% of the round himself. $3 billion. > he owns 90 PERCENT of the company (unheard of at this valuation) > deepseek was founded inside his hedge fund, one of China's most successful funds. guys a fucking beast. this round is meant to achieve 2 things: 1. acquire as much compute to push out new deepseek models more often 2. turn deepseek revenue-positive by pushing new enterprise products (same tactic as OAI and anthropic) deepseek v4.1 is expected to release soon.
English
@quantbeckman This is talking about signal-to-trigger mechanism for entries and exits? If so how is a proxy trigger defined? I'm assuming it's the direct signal post some sort of transformation function?
English
Today I had a conversation about triggers that made me think about this
English
Hmm moral of the story is they didnt have a real "system". When you don't have enough edge or are heavy in stat arb you rely on leverage, which is "short vol" and blows you up on tail events unless you have good hedging or uncorrelated alphas.
You don't see rentech blowing up because they're combining thousands of >0.7 sharpe alphas, low correlation, + hedged, per day.
English
This guy is the most overrated CEO today.
The Hill & Valley Forum@HillValleyForum
"We made a huge mistake. And 'we' being business, government, and military." Jamie Dimon on China: "There was this general assumption they'd become more democratic and more free. And it didn't really happen that way." "Too many people were changing the supply chains just because they're buying a piece of equipment for $10 less." "Business was making a lot of money there and they were like, 'Leave me alone.' It was a mistake." "We need to say: 'Can we, if they ever become an adversary, have all the things we need?' Now's the time to do it." The Hill & Valley Forum 2026 @HillValleyForum @jpmorgan @ChairmanG
English
@AgustinLebron3 Anyone who mentions agents or LLMs trading gets automatically laughed at by real quant traders and fund managers.
English
@quantbeckman all possible parameterizations and/or optimal controls?
English
@mean_field_zane I know some horny-ass 145+ IQers. They seem happy
English
@quantbeckman Path optimization in DRL can easily corner the policy into a dead end spiral
English
DRL model has negative annualized return, negative Sharpe, huge drawdown, and a -45.51% final PnL...
English
前段时间比较幸运，早期拿到了一个新的 DEX 白名单。平台一直对外强调自己是企业级 AI 量化交易系统，主打自动策略和智能风控。刚开始其实没太当回事，毕竟现在市场上很多 AI、量化更多只是概念包装。
不过既然有名额，就抱着验证的心态跑了一段时间。一个月下来，整体表现比预期要稳定，尤其是在震荡行情里，系统执行策略的纪律性明显比人工更强。
跑下来最大的感受是：现在的市场越来越复杂，很多时候人工交易输的不是判断，而是执行力和情绪管理。
量化系统可以 24 小时运行，不受情绪干扰，也能更快对市场数据做出反应。从效率和稳定性来看，AI 量化确实正在慢慢拉开和传统手动交易之间的差距。
中文
@GryptoGoon Devil's in the details of how it's implemented, & used.
x.com/HackworthAI/st…
Hackworth@HackworthAI
This is a simple demonstration why market regime models can provide quantitative or ML-based strategy a "base edge" and is far from obselete. Of the various regime types, below is a a benchmark of a trend regime model run on the largest volume Chinese Equity Index Futures (S&P500 Equivalent) which averages daily volume over $300B USD (competitive market). I didn't use BTC because its actually a lot easier, & wouldn't demonstrate my point.
English
