Experiential
355
Blog

Writing

Notes from Experiential Labs on the gateway, reliability, and the intelligence layer.

Reliability · August 2026

Failing over LLM providers without changing the model

The same model, sold by several providers, should survive any one of them failing. Which failures are allowed to spill, how the waterfall keeps model identity fixed by construction, what streaming and billing do under failover, and the five gaps that remain. From the open-source engine.

9 min
Reliability · August 2026

Hardened to carry all your traffic

A request through a gateway like ours normally costs seven database round trips. Ours makes two. The tricks that got it there, the region move that fixed the rest, failover that spans clouds, and the time we took our own gateway down on purpose. With the code.

11 min
Paper · June 2026

Size Doesn't Matter: Cosine-Scored Sparse Autoencoders

Inner product scoring conflates directional alignment with input magnitude. We propose cosine scoring for dictionary learning on normalized representations. ICML Spotlight.

2 min
Paper · June 2026

CLaaS: Continual Learning as a Service for Sample Efficient Online Learning

Online continual learning for deployed LLM agents behind a chat API: experience replay for gradient reuse, superior forward transfer, and less forgetting than in-context learning.

2 min