Skip to main content

Anthropic Deploys Multiple Claude Agents for 'Research' Tool - Says Coding is Less Parallelizable

1 month 1 week ago
In April Anthorpic introduced a new AI trick: multiple Claude agents combine for a "Research" feature that can "search across both your internal work context and the web" (as well as Google Workspace "and any integrations...") But a recent Anthropic blog post notes this feature "involves an agent that plans a research process based on user queries, and then uses tools to create parallel agents that search for information simultaneously," which brings challenges "in agent coordination, evaluation, and reliability.... The model must operate autonomously for many turns, making decisions about which directions to pursue based on intermediate findings." Multi-agent systems work mainly because they help spend enough tokens to solve the problem.... This finding validates our architecture that distributes work across agents with separate context windows to add more capacity for parallel reasoning. The latest Claude models act as large efficiency multipliers on token use, as upgrading to Claude Sonnet 4 is a larger performance gain than doubling the token budget on Claude Sonnet 3.7. Multi-agent architectures effectively scale token usage for tasks that exceed the limits of single agents. There is a downside: in practice, these architectures burn through tokens fast. In our data, agents typically use about 4Ã-- more tokens than chat interactions, and multi-agent systems use about 15Ã-- more tokens than chats. For economic viability, multi-agent systems require tasks where the value of the task is high enough to pay for the increased performance. Further, some domains that require all agents to share the same context or involve many dependencies between agents are not a good fit for multi-agent systems today. For instance, most coding tasks involve fewer truly parallelizable tasks than research, and LLM agents are not yet great at coordinating and delegating to other agents in real time. We've found that multi-agent systems excel at valuable tasks that involve heavy parallelization, information that exceeds single context windows, and interfacing with numerous complex tools. Thanks to Slashdot reader ZipNada for sharing the news.

Read more of this story at Slashdot.

EditorDavid

Bug Hits Some Threads Users: Their Words Echoed by All Other Users

1 month 1 week ago
Threads now has 350 million users — but this week a strange bug affected some Threads accounts (on both desktop and mobile). "One user's post will get repeated over and over again..." explains TechCrunch, "as though every user on your feed is saying the same thing." "Siri, unsubscribe me from 2025," one Threads user wrote, per a screenshot from social media expert Alexa Heinrich. But then, everyone else on Heinrich's feed appeared to be echoing the same cheugy joke... While it's not yet clear what caused the bug, Meta Communications Director Andy Stone responded to app researcher Jane Manchun Wong's post about the issue. "Whoops, well that clearly shouldn't have happened! We're working on getting it fixed now," Stone said. I thought the bug was only affecting user feeds (and not replies). But either way, Wong came up with the perfect comeback. "Whoops, well that clearly shouldn't have happened! We're working on getting it fixed now."

Read more of this story at Slashdot.

EditorDavid