If chip manufacturing advances allow them to eventually run leading edge models at speeds much faster than competition, that seems a really bright future all on its own. Their current chip is reportedly 5nm already, and much too small for the real 5.3-codex: https://www.cerebras.ai/press-release/cerebras-announces-thi...
We operate a postgres service on Firecracker. You can create as many databases as you want, and we memory-snapshot them after 5 seconds of inactivity, and spin them up again in 50ms when a query arrives.
the main area I'd like to see some departure from beads is to use markdown files (or something) to be able to see the issue context/comments better in a diff generated by git.
The other area I'd like to see some software engineering thinking that's more open ended is on regression testing: ways of storing or referencing old versions of texts to see if the agent can complete old transformations properly even with a context change that patches up a weakness in a transformation that is desirable. This is tricky as it interacts with something essential in software engineering, the ability to run test suites and responding to the outcome. I don't think we know yet when to apply what fidelity of testing, e.g. one-shot on snippets versus a more realistic test based on git worktrees.
This is not something you'd want for every context, but a lot of my effort is spent building up prompt fragments to normalize and clean up the code coming out of a model that did some ad-hoc work that meets the test coverage bar, which constrains it decently into having achieved "something." Kind of like a prototype. But often, a lot of ungratifying massaging is required to even cover the annoying but not dangerous tics of the LLM, to bring clarity to where it wrote, well, very bad and unprincipled code...as it does sometimes.
I was disappointed to see that this is still 10x the code needed for the feature set and that it still insists on duplicating state into a SQLite index for such minuscule amounts of data.
I've seen 25-30 similar efforts to make a Beads alternative and they all do this for some reason.
That would be billed as a single query. We think this is a much simpler way to reason about your cost compared to counting rows scanned, CPU time consumed or something more granular like that.
If your query is very expensive, it will take longer to complete, and that will be a signal to you the developer to simplify your query or identify an index that can help speed it up. Prisma Optimise will help you identify and improve such queries.
While I think as an arm-chair business wonk y’all should count it as 6 queries and not 1 as a payer and consumer I’m even more likely to use it now that you count us as only a single query. :-)
