Perplexity Interactive Brokers for a small desk, priced line by line: about $100 a month, two scheduled tasks, full prompts, and why AI never trades.
Jiri’s Insights
Software Engineering Isn’t Dead. Typing Is.
Is software engineering dead now that AI writes 75% of Google’s new code? No. Typing is. The arithmetic, six silent defaults and 24 jobs AI can’t own.
Does AI Trading Have an ESG Problem? Yes — Unless You Use ESG as a Lens, Not a Label
Does AI trading have an ESG problem? Yes, three. My CFA Institute deck: the E, S and G lenses, the Receipt–Person–Stop ledger and six questions to ask.
Does AI Trading Have an ESG Problem? Sustainability Is P&L You Haven’t Measured Yet — Join Us at CFA Institute Sustainable Investing Community Event on 30 September
Does AI trading have an ESG problem? Join me, Philip Sun and Jared Broad at CFA Institute on 30 Sep for the AI Sustainability Ledger and a 90-day playbook.
The Kronos Foundation Model Has 38,117 GitHub Stars — and Every Backtest Inside Its Training Window Is a Memory Test
Kronos foundation model review: why every pre-release backtest is a memory test, plus a walk-forward QuantConnect protocol and deflated Sharpe math.
AI Text Watermarking Measures the Wrong Thing — And Anthropic Just Admitted It
AI text watermarking just went live on Claude worldwide. One paraphrase pass kills 98% of the signal. Here’s why the whole scheme is broken.
One Prompt, One Stock, 360 Runs: How an LLM Gets a Trade Right and Still Can’t Be Trusted With It
On 2 February 2022 Meta lost $230bn in a day. I gave a language model one careful prompt and ran it 360 times on that print. It called the direction right 60 times out of 60 — and produced 13 different trades. Here are the nine pitfalls, and the skill that fixes them.
The LLM Ran the Backtest. That’s Exactly Why You Should Panic.
TL;DR: For a year the standard critique of LLM-designed strategies was “the model can’t actually do the math — the backtest is hallucinated.” That critique is now dead. ChatGPT, Claude…
Your LLM Doesn’t Pick Stocks — It Remembers Them
TL;DR — Robo stock-picking is forecast to grow roughly 600% by 2029, and a ChatGPT-picked basket is genuinely beating the UK’s most popular funds. But most “AI beats the market”…
“Make Medallion Fund”: I Ran the Viral One-Prompt Strategy. $1 Became $0.02.
I took the viral “make medallion fund” prompt literally and backtested it. $1 became $0.02. Here’s where LLM alpha actually lives.