Katelyn Lesse says Anthropic opposes distillation because copied models could run without its safety classifiers.
“If someone distills our models, and they run those models without safeguards, classifiers, there could be bad outcomes in the world”
Person
Katelyn Lesse
1 episodes · 15 quoted claims
Anthropic shipped an API compaction feature to replace customers' manual compaction, so it works with preserved thinking blocks.
“we shipped a new, um, compaction feature within the API to replace what they had otherwise been doing manually, but still works with preserved thinking”
Katelyn Lesse says Opus 5.5 does not carry the data retention requirements that apply to Fable.
“does not have those data retention requirements that Fable has”
Katelyn Lesse says Anthropic used a trust grant to grandfather existing customers when preserved thinking was first required for Fable 5.1.
“we kind of grandfathered in some people and gave a bit of a, you know, just, like, a”
Katelyn Lesse says that when she joined Anthropic, the Messages API was a Python monolith running in a single GCP region.
“we had the Messages API. It was a Python monolith. We were running it in a, you know, single GCP region”
Katelyn Lesse says CPU capacity can no longer be scaled on demand and now has to be planned in advance.
“now it becomes something that you have to, um, capacity plan for in advance”
Anthropic built a full Rust fork of its Messages API and ran shadow traffic through it to compare outputs with the Python version.
“we literally built, like, an entire fork of the entire API in Rust, and then started running shadow traffic through it”
Katelyn Lesse says the Rust rewrite of the Messages API saved roughly 40 to 50% of CPU.
“somewhere like 40 to 50%, something like really crazy”
Katelyn Lesse says the Rust rewrite improved time to first token by roughly 10 to 20%.
“somewhere between like 10 and 20%, um, improvement on like time to first token specifically”
Katelyn Lesse says Claude Managed Agents is a suite of APIs above the Messages API, which provides raw token access.
“Claude managed agents is our API today. We have the Messages API, which is essentially raw token access.”
Katelyn Lesse says Anthropic's first design for an agent API put Claude Code in a sandbox behind an API, but it was slow to start and lost the agent when the sandbox died.
“our 1st iteration of an API for agents was just, like, throw Claude code in a sandbox and, like, shove an API on top.”
Katelyn Lesse says Claude Managed Agents runs the harness on a durable server and only spawns a sandbox or container when execution is needed.
“if the harness is just running on a durable server and it's only spawning a sandbox or a container to execute when it needs it”
In Claude Managed Agents, credentials are stored in a separate vault, the agent sees only a placeholder, and an egress proxy injects the real credential.
“the agent only ever sees, like, a placeholder, right? And, like, on egress, we have a proxy that goes and, like, pulls the right credential out and injects it”
Katelyn Lesse says Anthropic created separate developer relations teams for the Claude Platform and for Claude Code.
“we ended up spinning up a devrel team within platform and a devrel team within cloud code.”
Katelyn Lesse says Anthropic's developer relations team owns the Claude API skill that helps coding agents build integrations against the API.
“the Claude API skill that helps people build against the API is owned by our devrel team”