Chinese artificial intelligence company DeepSeek has outlined a new design intended to make AI coding assistants more autonomous, allowing them to handle multiple tasks with less human intervention. According to a paper from the company’s DeepSeek Harness team, cited by Singapore’s South China Morning Post on Sunday, the goal is to reduce the amount of human effort needed to coordinate and monitor several AI agents at once. The team said multi-agent management is constrained not only by model capability but also by human attention, arguing that a single person can supervise only three to five active AI agent sessions at the same time. Under the proposed setup, tasks would be distributed across agents and their work coordinated by the system, while humans would focus on reviewing outputs and making decisions. The report said the proposal arrives as competition among AI developers intensifies, including among US firms Anthropic and OpenAI. Cointelegraph also noted that it reported in October that Chinese AI models had outperformed US peers in cryptocurrency trading tests, citing CoinGlass data, with DeepSeek posting the only positive unrealized return at 9.1%.
Chinese artificial intelligence company DeepSeek has presented a design meant to give AI coding assistants more autonomy, allowing them to carry out multiple tasks with less human intervention.
According to a paper published by the company’s DeepSeek Harness team and cited by Singapore’s South China Morning Post on Sunday, the goal is to reduce the human effort required to coordinate and monitor multiple AI agents.
Paper points to human attention as a bottleneck in multi-agent work
The DeepSeek team said managing multiple agents demands human attention, adding that “single-task limits depend on model capabilities, while multitask limits depend on human attention.”
The paper said one person can oversee only three to five active AI agent sessions at the same time. In the proposed system, tasks would be distributed among agents and their work coordinated, leaving humans to review results and make decisions.
Proposal emerges as AI competition heats up
The South China Morning Post said the proposal comes at a time of intense competition among AI developers, including US companies Anthropic and OpenAI.
Cointelegraph referenced DeepSeek’s earlier crypto trading results
Cointelegraph said in an October report that Chinese artificial intelligence models had outperformed US counterparts in cryptocurrency trading, citing data from blockchain analytics platform CoinGlass.
In that trading experiment, DeepSeek led the field and was the only AI model to produce a positive unrealized return, at 9.1%. Cointelegraph said the result surprised crypto traders because DeepSeek was developed at a fraction of the cost of its US rivals.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
