See More

Vitalik Buterin Tests Reveal ChatGPT’s Trading Potential

2 mins
Updated by Geraint Price
Join our Trading Community on Telegram

In Brief

  • Ethereum co-founder Vitalik Buterin has proved that ChatGPT can find software libraries that lower the barrier to entry for amateurs.
  • He successfully accessed geolocation data through APIs suggested by the AI tool.
  • His experiments reveal the potential for ChatGPT to be used to suggest APIs needed for developing successful crypto trading strategies.
  • promo

Ethereum co-founder Vitalik Buterin finds that while ChatGPT is limited, it exposes amateurs to software libraries they can use to formulate more meaningful answers.

ChatGPT offered Buterin application programming interfaces (APIs) to calculate how the distance between two points relates to the travel time between them.

ChatGPT Can Help Traders Develop Custom Tools

The artificial intelligence (AI) bot offered Buterin assistance writing a script to access publicly-available data from GeoLife and compute the distance between two points using a Google Maps API.

It also helped Buterin write code to create a scatter plot of time-distance pairs on the first try and itself wrote a script to interpret GeoLife’s location data.

However, the bot could not supply any APIs to calculate the optimal route, including flights, between two points more than 500 km apart.

Computers interpret commands in a script and execute them immediately without needing to compile them in high-level programming languages like Solidity. Solidity compilers, for example, can convert human-readable smart contract code into ones and zeros that the Ethereum Virtual Machine understands.

AI Can Benefit Traders

Vitalik Buterin’s experiment reveals that while AI tools like ChatGPT can fail to produce accurate answers on the fly, they can speed up the development of custom tools that traders can benefit from.

San Francisco-based prime broker FalconX recently announced a new artificial intelligence tool called Satoshi to offer trading advice. The tool would assist users in employing software-based trading strategies based on a specific portfolio or market scenario. It uses a similar large language AI training model to ChatGPT. The tool is still in its infancy.

Like Buterin, traders can ask ChatGPT to write a script corresponding to their strategies. For example, a trader can already use the tool to outline the steps of a specific stock trading strategy. The trader can then choose to implement the plan in a script or ask the tool to do so. 

Mean Reversion Apple Trading Strategy in ChatGPT
Mean Reversion Apple Trading Strategy | Source: Quantra

In December last year, an award-winning AI writer and trader, Michael King, used ChatGPT to create a script to trade BTCUSDT on Binance. The AI tool provided API functions he needed to place a market buy order above Binance’s minimum threshold.

Example of ChatGPT BTCUSDT Market Buy With Minimum Order Size
BTCUSDT Market Buy With Minimum Order Size | Source: Michael King

However, as in the case of Satoshi in its current form, ChatGPT itself cannot account for complex or unforeseen market conditions. Traders must also be aware of AI hallucinations, where a fallacy is convincingly presented as fact. 

Also, Buterin noted that ChatGPT could occasionally generate incorrect results based on words used in a query.

Therefore, interpreting whether a trading script’s results are correct requires a minimum level of coding expertise.

For Be[In]Crypto’s latest Bitcoin (BTC) analysis, click here.

Top crypto projects in the US | April 2024

Trusted

Disclaimer

In adherence to the Trust Project guidelines, BeInCrypto is committed to unbiased, transparent reporting. This news article aims to provide accurate, timely information. However, readers are advised to verify facts independently and consult with a professional before making any decisions based on this content. Please note that our Terms and ConditionsPrivacy Policy, and Disclaimers have been updated.

David-Thomas.jpg
David Thomas
David Thomas graduated from the University of Kwa-Zulu Natal in Durban, South Africa, with an Honors degree in electronic engineering. He worked as an engineer for eight years, developing software for industrial processes at South African automation specialist Autotronix (Pty) Ltd., mining control systems for AngloGold Ashanti, and consumer products at Inhep Digital Security, a domestic security company wholly owned by Swedish conglomerate Assa Abloy. He has experience writing software in C,...
READ FULL BIO
Sponsored
Sponsored