causal claim
Because deep-research agents are read-only and cannot affect the world, the speaker considers it safest to run many of them.
swyx · ⚡️Anthropic vs Cognition on Multi-Agents: A Breakdown with Dylan Davis · 5 Jul 2025
In their words
The transcript segments this claim was taken from
“offer write access to the world so deep research is read only so it's the safest to just spam out as many as you want because it will never have side effects on the world”12:42Report a misattribution
0.90how strongly it was put, not whether it is true
0.75importance to the conversation
0.90confidence the claim was read correctly