A recent spate of applications built on OpenAI’s GPT-4 API has the cryptocurrency community buzzing with designs towards the development of a fully autonomous and self-correcting cryptocurrency trading bot.
AutoGPT set to 100 runs. Goal: amalgamate best indicators for Crypto trading in Pine code. Result looping errors. Scavenged through output, found enough bits for GPT4 to give me strategy Pine code. 4hr backtested 2018 to now. $25 to $92M. Started test today, currently $1 profit
— Under_the_Valley (@ValleyUnder) April 11, 2023
Two of these apps, dubbed “BabyAGI” and “AutoGPT”, have received particular attention from many users trying to build cryptocurrency trading apps on top of them.
The big idea behind both apps is task management for GPT-4. GPT-4 currently excels at natural language processing, as demonstrated by the demonstrable utility of the ChatGPT interface, but lacks memorization capabilities.
Applications built on top of the GPT API are basically limited to single session usage, which means that the model cannot remember information from previous interactions. This has to do with the amount of data (called “tokens”) required by individual queries and with GPT’s tendency to hallucinate, a problem that becomes more and more apparent as the number of tokens increases.
Basically, users start from scratch every time they query the machine. In terms of building a cryptocurrency trading application capable of self-correcting and historiographical analysis – adjusting to market conditions in real time, while keeping short-term and long-term trends in focus – this means that even the A more robust bot built on top of the GPT API would normally require strong human supervision.
Some clever developers may have discovered a possible way around these limitations by building applications that take advantage of GPT’s ability to generate code and connect to external sources.
We’ve seen our fair share of trading bots, but the goal of these particular apps goes beyond simply automating cryptocurrency news aggregation or teaching a machine learning broker to recognize a drop.
AutoGPT, for example, uses GPT-4 to generate code and then exploits GPT-3.5 as what appears to be a virtual artificial memory space in which information is combined and passed from one to the other.
Another initiative, BabyAGI, combines GPT-4 with LangChain, a coding framework, and Pinecone, a vector database, to generate new agents that complete complex tasks without losing sight of the original goal.
Both applications could serve as the basis for a multi-agent artificial intelligence application capable of managing a cryptocurrency portfolio from top to bottom simply by giving instructions in plain language.
While neither app appears to have been specifically designed with the cryptocurrency market in mind, we have seen various efforts on social media and on GitHub to adapt one or both for standalone trading.
#AutoGPT using #GPT4 finds another article on the Forbes website.
PLAN:
-Browse the Forbes article
– Identify the top AI cryptocurrencies
– Add each currency to my list of top contenders
CRITICISM: I must ensure that I consider multiple sources and compare the information.. pic.twitter.com/Lbh24eX18X– Mr. Harrison (@Harriso20462924) April 9, 2023
Clarification: The information and/or opinions expressed in this article do not necessarily represent the views or editorial line of Cointelegraph. The information presented here should not be taken as financial advice or investment recommendation. All investment and commercial movement involve risks and it is the responsibility of each person to do their due research before making an investment decision.
Investments in crypto assets are not regulated. They may not be suitable for retail investors and the entire amount invested may be lost. The services or products offered are not directed or accessible to investors in Spain.