Post by @boneGPT
32% credible (35% factual, 25% presentation). The claim of 200% gains from an LLM-based 'degenerate' trading strategy lacks long-term verification and context on risks, with evidence limited to short-term gains in screenshots. The presentation is biased and omits crucial details on time frame, drawdowns, and backtesting, contributing to the low credibility assessment.
Analysis Summary
The post claims that instructing an LLM to trade in a 'retarded degenerate' manner resulted in a 200% portfolio increase, mocking algo traders' emphasis on data analysis expertise. The evidence from attached screenshots shows short-term gains for a 'Degenn' bot, but lacks long-term verification and context on risks or sustainability. Opposing views highlight that such high returns in trading bots are often unverified hype, with studies on LLM trading strategies indicating mixed or short-period performance without consistent outperformance.
Original Content
The Facts
The claim of 200% gains from an LLM-based 'degenerate' trading strategy appears exaggerated or selective, given the author's history of satirical and unverified posts; screenshots show apparent short-term profits but omit risks, drawdowns, or backtesting details. Verdict: Likely Hyperbolic or Unverified – Bayesian update from 20% base rate prior for such trading claims (due to common hype in crypto/AI trading) to ~10% posterior, factoring low author truthfulness (45%) and bias toward anti-hype sensationalism.
Benefit of the Doubt
The author advances a satirical, anti-establishment perspective mocking professional algo trading and AI expertise requirements, positioning simplistic LLM instructions as superior to data-driven analysis. Key omissions include trading risks, time frame of gains (likely short-term volatility in crypto), lack of independent verification, and failure to disclose potential losses or bot parameters, which shapes perception toward overconfidence in untested strategies. This selective framing boosts engagement through controversy while downplaying the complexity and frequent failures in LLM trading, as noted in research on underdeveloped evaluation practices.
Visual Content Analysis
Images included in the original content
VISUAL DESCRIPTION
Dark-themed dashboard screenshot showing a line chart of portfolio value over time starting from $1,000, rising sharply to around $4,285, with colored lines for multiple strategies (purple, yellow, etc.); below the chart are three portfolio overviews labeled 'Ruthless' (net loss), 'Mastermind' (slight loss), and 'Degenn' (gain of $420.10 or 20.10%).
TEXT IN IMAGE
Portfolio Performance $4,285 Portfolio Overview Ruthless $1,077.77 $2,049.40 Mastermind $800.25 $810.51 Degenn $1,320.10 $1,056.56 $420.10 (20.10%)
MANIPULATION
Possible selective cropping or editing to highlight only positive periods; no visible artifacts like deepfakes, but the 20.10% gain contradicts the post's 200% claim, suggesting exaggeration or different scaling; inconsistencies in percentage vs. absolute values raise doubts.
TEMPORAL ACCURACY
Image aligns with post date (2025-10-23) based on UI style and recent trading bot aesthetics; no dated elements, but context from X posts indicates live or recent simulation.
LOCATION ACCURACY
No geographical claims or clues in the image; it's a digital screenshot of a trading interface, not tied to a physical location.
FACT-CHECK
The chart purports to show real-time bot performance with 'Degenn' up 20.10%, but this is far below the 200% textual claim; reverse image search yields no matches to known scams, but similar unverified trading screenshots are common in hype posts; research on LLM trading (e.g., arXiv papers) shows short-term gains possible in volatile markets like crypto but not sustainable 200% without high risk.
How Is This Framed?
Biases, omissions, and misleading presentation techniques detected
Fails to provide details on time frame, risks, drawdowns, or verification of the 200% gains, presenting short-term profits as straightforward success.
Problematic phrases:
"it's up 200%""just tell the LLM to be retarded"What's actually there:
Short-term gains shown in screenshots without long-term data or risk disclosure
What's implied:
Sustainable, risk-free 200% returns from simplistic instructions
Impact: Leads readers to overestimate strategy viability and underestimate trading complexities, fostering misguided confidence.
Implies direct causation between crude instructions and 200% gains without evidence, ignoring market volatility or luck.
Problematic phrases:
"i told the LLM to trade like a retarded degenerate and it's up 200%"What's actually there:
No substantiation of instruction leading to gains; high-level context notes mixed LLM trading performance
What's implied:
Degenerate instructions cause superior returns
Impact: Misleads readers into believing simplistic prompts outperform expert methods, promoting untested replication.
Highlights 200% gain while neglecting overall portfolio risks, time period, or comparative benchmarks.
Problematic phrases:
"up 200%"What's actually there:
Short-term crypto volatility gains per screenshots, no backtesting or loss details
What's implied:
Impressive, scalable success metric without qualifiers
Impact: Inflates perceived magnitude of achievement, encouraging risky behavior by obscuring true scope of variability in trading.
Presents one instance as evidence against established trading norms, implying a trend of LLM superiority.
Problematic phrases:
"all the algo traders told me... they lied"What's actually there:
Isolated anecdote vs. studies showing inconsistent LLM trading
What's implied:
Pattern of expert advice being wrong
Impact: Creates illusion of a reliable pattern from a single event, eroding trust in data-driven approaches.
Sources & References
External sources consulted for this analysis
https://arxiv.org/html/2505.07078v3
https://arxiv.org/html/2505.07078v1
https://automatedtradingstrategies.substack.com/p/llm-trading-strategies-update-plus
https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1608365/full
https://arya.ai/blog/5-best-large-language-models-llms-for-financial-analysis
https://www.esma.europa.eu/sites/default/files/2025-06/LLMs_in_finance_-_ILB_ESMA_Turing_Report.pdf
https://arxiv.org/html/2505.07078v2
https://x.com/boneGPT/status/1968849630424109093
https://x.com/boneGPT/status/1925213980877820166
https://x.com/boneGPT/status/1884274734398882144
https://x.com/boneGPT/status/1883611351009862005
https://x.com/boneGPT/status/1921293468762079680
https://x.com/boneGPT/status/1964858432198221833
https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1608365/full
https://www.inoru.com/blog/how-does-building-llm-for-trading-data-improve-market-analysis-in-2025/
https://arxiv.org/html/2505.07078v3
https://arxiv.org/html/2505.07078v1
https://www.sciencedirect.com/science/article/pii/S2590005625000177
https://www.esma.europa.eu/sites/default/files/2025-06/LLMs_in_finance_-_ILB_ESMA_Turing_Report.pdf
https://arxiv.org/html/2503.21422v1
https://mend.io/blog/llm-security-risks-mitigations-whats-next
https://verifiedmarketreports.com/product/large-language-model-llm-market
https://www.softwebsolutions.com/resources/llm-use-cases.html
https://www.hostinger.com/tutorials/llm-statistics
https://capitole-consulting.com/blog/turing-to-autonomous-agents-2025-llm-ecosystem
https://automatedtradingstrategies.substack.com/p/llm-trading-strategies-update-plus
https://www.inoru.com/blog/how-does-building-llm-for-trading-data-improve-market-analysis-in-2025/
https://x.com/boneGPT/status/1965236353731379478
https://x.com/boneGPT/status/1953659985356877837
https://x.com/boneGPT/status/1968849630424109093
https://x.com/boneGPT/status/1921293468762079680
https://x.com/boneGPT/status/1925213980877820166
https://x.com/boneGPT/status/1884274734398882144
Want to see @boneGPT's track record?
View their credibility score and all analyzed statements