LLMs each trading $100K vs. a frozen rulebook
the rulebook leads
Details
- External ID
- 49330386
- Source
- HN
- Company
- —
- Product
- LLMs each trading $100K vs. a frozen rulebook
- Website domain
- aitradingcompetition.com
- Launched
- Aug. 17, 2026
- Cohort
- —
- Upvotes
- 12
- Upvotes percentile
- 0.6364247311827957
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:32 a.m.
- Updated at
- Sept. 10, 2026, 5:32 a.m.
Enrichment
- Theme
- algorithmic trading bots and platforms
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- game simulating llms versus fixed rules
- Manually corrected
- False
Could you build this?
Partial A web dashboard logging paper trades and calling LLM APIs on daily market feeds is straightforward, but maintaining low-latency historical financial data feeds, portfolio accounting, and error-proof paper-execution engines is tricky.
What it would actually take: Architecture requires a Python/Go backend connected to market data APIs (e.g., Polygon.io, Alpaca), a scheduler running prompt templates through LLM APIs to generate trade orders, and a robust accounting engine tracking splits, dividends, slippage, and PnL. The hard part is building a reliable simulation/backtesting framework that avoids lookahead bias and handles erratic LLM trade syntaxes.
Discussion
3 comments analyzed.
Competitors mentioned: GPT-5.6, Claude, Grok, Gemini
Concerns raised: Paper trading results don't translate to live trading (4x slippage gap), AI models underperform static rulebooks despite daily rewriting, High-churn strategies lose money due to real execution costs, Game-playing reasoning doesn't transfer to market trading, Limited sample size and upmarket bias
Competitors
Other products that read as similar to this one — 172 launches clear the similarity bar, closest 8 shown.
Attention rank: #70 of 173 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 291 days after the earliest competitor.
- LLMs as Planners, Not Reasoners · hn · 2026-04-07 · 7 upvotes · similarity 0.55
- Mage: Legal Diligence for M&A and Financings. Minutes, Not Days. · yc · 2026-01-31 · 8 upvotes · similarity 0.50
- We charge $10/mo for wealth management that costs $100 elsewhere · hn · 2025-11-13 · 7 upvotes · similarity 0.45
- Anneal · hn · 2026-03-25 · 7 upvotes · similarity 0.45
- Buyout Game Benchmark: Multi-Agent Bargaining, Transfers, and Takeovers · hn · 2026-03-30 · 6 upvotes · similarity 0.43
- Peer Arena · hn · 2025-12-28 · 5 upvotes · similarity 0.43
- Fillbook · ph · 2026-09-09 · 1 upvotes · similarity 0.43
- KillSwitch · hn · 2026-09-19 · 10 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.