Curious whether the biggest value has been performance debugging itself or helping developers understand system behavior they otherwise wouldn't have visibility into.
Sometimes the observability layer ends up being more valuable than the optimization layer.
Thanks! I think most performance debugging happens during development, what we're bringing to the table is exposure of system behavior in production which often diverges because of changes in the shape of workloads from dev, which are often simplistic and synthetic. So I'd say its late-stage performance debugging and production observability combined that makes this useful.
Stay tuned for a follow on post where we show how we used this to optimize an FSST decompression kernel for vortex (https://github.com/vortex-data/vortex).
Curious how many people are finding that context management has become a bigger bottleneck than model quality.
We've experimented with a few different workflows and the biggest failures usually aren't because the model can't code—they happen when the model loses track of project conventions, previous decisions, or why something was built in the first place.
Has anyone found a workflow that solves that well at scale?
Curious what you're seeing from users after the initial setup.
Do most people want a private environment primarily for security reasons, or because they eventually want long-running agents and workflows that they can fully control?
Seeing interest across the board. It’s not just security - many users want a full end-to-end dev environment where they can test, deploy quickly, and eventually run longer-lived agents/workflows with more control. Some want to run CI/CD and test stuff in parallel or with different use cases or eval cases.
We've found that grounding works reasonably well until the underlying knowledge starts changing frequently, at which point retrieval quality becomes much more of a state-management problem than a search problem.
Are most users treating Tkcore as a knowledge layer for relatively static information, or are you seeing teams use it for fast-changing operational data as well?
Curious whether the biggest value has been performance debugging itself or helping developers understand system behavior they otherwise wouldn't have visibility into.
Sometimes the observability layer ends up being more valuable than the optimization layer.