Perhaps this is pedantic, but this equivalence is ignoring fees, spread, and slippage, right?

Joe Dart elected president Y/N

Cory Wong elected president Y/N

A no bet on Joe Dart is not a yes bet on Cory Wong.

Edit: conversely, if the average no costs _more_ than 73 cents, but the 73% of all polymarkets resolve to No, that would imply that an everything-always-happens strategy is profitable (neglecting slippage)

I bet the average price for a no bet across these markets is 73 cents.

Comments URL: https://news.ycombinator.com/item?id=47723118

Points: 2

# Comments: 0

This is basically the same price as the cheapest options on Hetzner: https://snipboard.io/C9epWo.jpg. Sure my old laptop does have more RAM and a bigger SSD, but I bet it's also less reliable than Hetzner's servers, and is likely to suddenly die some day. So is the tradeoff really worth it? It's hard for me to believe that this is a genuine improvement for most things. The only definite winning case I can think of is if I have a process I want to run, but I don't care if it just suddenly stops working. But when would that ever be the case? and to save a couple dollars per month?

Edit: Maybe this is what github is doing :P

I'm extremely doubtful of this. It doesn't save time to tell it "you have an error on line 19", because that's (often) just as much work as fixing the error. Likewise, saying "be careful and don't make mistakes" is not going to achieve anything. So how can you possibly tweak the agent to "do it right" reliably without human intervention? That's not even a solved problem for working with _humans_ who don't have the context window limitations, let alone an LLM that deletes everything past 30k tokens.

What does "all the data" mean here? I see you mentioned SEC posts. What about news articles, twitter / blog / other posts, general info on the industries, etc?

I assume these are simulated trades, not real trades being executed. How accurately do you take into account trading fees, time from order-decision to order-placement, and things like this?

I would be interested to see the same test run on some prediction market (kalshi / polymarket / etc). In the stock market, a rising tide lifts all boats, so it's easy to deceive yourself about how well you've done, vs how important initial timing was. I suspect that prediction markets will eliminate that source of noise, since it's truly a 0 sum game. That said, it also adds lots of complication, insider trading will eat into your performance more, etc.

Personally I believe LLM-assisted trading is destined to underperform passive indices, so I also would have moved on from this. But you say results were promising, so I'm interested to hear why you're not pursuing it further. Is it just that you have other things to focus on? Is there something else that's making you move on?