Claude Science is really an agent harness with an arbiter daemon

A teardown of build 0.1.15-dev shows that behind the familiar interface, Claude Science runs a daemon that holds permissions and history, while the Python and R kernels keep only working state. The signed 111 MB app is just a loader: it unpacks a roughly 3.9 GB install, about 95% of which is separate execution environments.
The generated code calls host with no host package present in the environment. kernel_worker.py shows the daemon injecting the SDK through the first execute() after kernel start, with host.llm() and host.mcp() going out as synchronous RPC across the process boundary. Even faking a raw _host_call(“mcp”, ...) in the analysis kernel won’t return a capability: the daemon checks permission before dispatch.
Up next
AMD to invest up to $5 billion in Anthropic
AMD will invest up to $5 billion in Anthropic, per Reuters citing The Wall Street Journal. In return, Anthropic will deploy up to 2 gigawatts of AMD Helios rack systems on Instinct MI450 accelerators.
Related stories
- Anthropic bought a biotech with one full-time employee
- A perfect refusal score isn’t a safer model, Anthropic says
- Anthropic touts 94.2% true positives; curl rejected 19 of 34
- Anthropic’s IPO filing says a key safety threshold is met
- 1,000 Claude agents redid the Fermat proof in 28.7 hours
- Claude Fable 5.2 hits 69% on PCB layout test, up from 25%
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

