The past few weeks (or months) have been an interesting period for oil traders. Oil prices spike up and down in tandem with the US-Iran situation and the Strait of Hormuz closure.
Oil markets on Polymarket get a lot of volume on the monthly/weekly markets, yet daily Up Down markets volume remain quite small. Though, they’re small enough for an oil trading experiment with $10-$30 in size per bet. Perfect for a Hermes trading experiment.
0xJeff@0xJeff
Just learnt that Hermes might just be amazing at Oil Trading after all 4 Wins with ~63% ROI (albeit with a small bankroll) Ran an experiment that lets Hermes auto-trade on Oil Daily Up Down market Hermes started with $200 bankroll, leverages Synthdata daily forecast oil
0xJeff @0xJeff
Man... AI is cheap but it's so expensive Cost to get started (inference per 1M token) went from $18.40 to $6.07 (3x cheaper in a year) But the cost to continuously run it (agentic workflows) is 23.4x more expensive On top of this, more users are adopting AI, and each user https://t.co/G0COcA9f2K
2:51 PM · Jul 23, 2026 · 44.3K Views
21 Replies · 6 Reposts · 92 Likes
The funny thing is I had my first 2 losses right after this post
The current stat is now 4W/2L (66% WR)
The experiment is fairly simple - let Hermes agent make 1 bet daily based on Synth signals.
Synth runs a 24/7 competition where miners compete to predict the price path of assets (commodities, equities, crypto). The more accurate you are, the more rewards you’ll get.
What I did is basically plugging in Synth API + Polymarket API into Hermes and point it towards Daily UP/DOWN oil market.
If the Synth signal has more confidence than Polymarket consensus by at least 2% (positive delta), Hermes executes the trade.
Or if the Synth signal directionally diverge from Polymarket consensus by more than 8% (negative delta), Hermes executes the trade based on its signal.
So far, the 4 wins were from the last oil run up when US-Iran tension escalated.
While Synth appears to be pretty good at predicting volatility, it doesn’t recognize catalyst events. The probability didn’t take into account the de-escalation event that happened during last weekend.
This resulted in Synth showing 40% YES on UP market today while the Polymarket YES odd was only at 5% (reflecting the de-escalation).
And so I added a Gap-Event filter with 4 tiers of severity.
If the price gap between current price and prior close is
<1.5% — Proceed
1.5% - 2.5% — Scale half Kelly size
2.5 - 4.0% — Scale quarter Kelly size
>4.0% — Skip execution entirely
This layer would help prevent unnecessary losses during catalysts-driven periods.
Model: DeepSeek v4 Flash
Data: Synth API
Execution: BlockRun (x402 pay-per-use), helps get over geoblocking. Polymarket CLOB API is also usable if you’re not getting geoblocked by Polymarket
Since trade decisions are pure Python, it doesn’t really matter whether the model is v4 Flash or Pro or Kimi K3.
I run a cron job daily in the morning. If Hermes sees an opportunity, it’ll make a trade. If not, we’ll see again tomorrow.
The hope is to see if the agent can reliably make money trading short-term prediction markets and pay its own inference.
If not, I might consider finding more data sources, looking for better edge. At the very least, it can serve as a fun experiment for me to test out APIs.
Thanks for checking out the article, if you have any feedback or questions, feel free to drop them below
Check out the articles below (if you haven’t yet)
Hermes as the Ultimate Analyst — I’ve found the gist for my ultimate analyst
1 Month with Hermes — I’ve been using Hermes wrong all along
Hermes, $200 and 30 skills later — here are the 3 skills that’re worth it
Disclaimer: This article is provided solely for informational and educational purposes and may not be redistributed, reproduced, or modified. The insights presented reflect our own research and judgment and should not be interpreted as endorsements or recommendations. Nothing in this article constitutes financial, investment, or professional advice. Market conditions are inherently uncertain, and asset values can fluctuate significantly including the possibility that an investment may decline substantially or even lose its entire value. All investments involve risk. Any financial decisions you make after reading this article are entirely your own, and we do not accept liability for any losses or results that may follow. Readers should conduct their own independent research before making any financial decisions.
If you’re having any trouble with email delivery, payments, cancellations, un-subscriptions, or refunds, the best first stop is the Substack Help Center for Subscribers or Substack Support as they are great at sorting out those issues.
If your concern isn’t fully resolved or you need additional help regarding your subscription, we are here for you. Just reply to this email (if you’re reading it in your inbox) or send us a message through our Substack page.
Getting in touch with us helps ensure any issue is addressed promptly and that your access to our future activities and community channels continues smoothly.
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.