I'm always curious what you guys are working on; every git repo I've run a local model on and stick below <100k to increase speed seems effective enough to scope patches and changes.

▲ _zoltan_ a minute ago | parent | next [-]

I have a couple projects where the background research is easily over 500k without writing any code, after ultracode subagents synthesis.

▲ KronisLV 42 minutes ago | parent | prev | next [-]

My current Claude Code session has been going on for like 35 hours and has used up around 400 million tokens, thankfully almost all of those being cached (95-98%) - pretty typical for long form agentic work.

First you spend like 2-3 hours working on a plan, once you have that you just tell the model to go and implement it, do adversarial sub-agent review loops before each commit and also make sure that all tooling and tests pass (including coverage requirements). You do need to poke it in a slightly different direction every few hours, though. Not even any novel work, just some refactoring and SSE notification hardening, bug fixes, alongside environment tuning and getting rid of some bottlenecks (also migrated from Oracle to PostgreSQL but that's mostly done).

That said, Kimi somehow manages to use less context in the main thread than Anthropic's models (even when you use sub-agents and also dynamic workflows in Claude Code), might have something to do with either how the model is tuned or their Kimi Code harness - because even in most of the longer form sessions it doesn't seem to fill up quite as quickly (note: because the kimi vis tool doesn't have a full summary view across all agents, these are the main long running agent stats across some sessions, not sub-agents):

  total tokens    cache hit rate    wall time    peak context
  283M            98%               3963m        466k
  258M            97%               2724m        467k
  98M             94%               1353m        393k
  67M             97%               614m         434k
  75M             98%               1447m        498k
  53M             99%               191m         375k
  6M              96%               139m         124k
  7M              98%               86m          118k
  11M             99%               61m          147k

I could see 256k context being sufficient for all sorts of work, even if intermediate progress/plan tracking files and docs might have to be used along the way, in addition to whatever plan support the harness has (for example, if you document something that will be relevant for load testing you might need that in 10 turns but not during the ones before then).

	▲	bkaae 21 minutes ago \| parent [-]
		Thanks for sharing - is this a normal feature request you are implementing in this example or is this a project from scratch? Trying to get an idea of how your workflow compares to mine.

▲ giancarlostoro 25 minutes ago | parent | prev | next [-]

I had Claude build me a Python-inspired .NET language that treats .NET as a first class citizen, and breaks backwards compatibility where some Python nuances don't really apply to .NET for. I was able to get it to build a sample ASP .NET Web application that ran on Culebral code.

Haven't gone back to it, have been using Claude Code on a private project I'm still architecting.

https://github.com/Giancarlos/Culebral

▲ sheeshkebab 24 minutes ago | parent | prev | next [-]

Try doing a refactoring of some sort or larger new feature using just an agent on a moderately sized codebase, 256k will be compacting every few minutes, and result will be unusable.

▲ jdoe1337halo an hour ago | parent | prev [-]

They are just talking to the model in CC, while staying in a single thread. Doubt they have any actual coding knowledge to compartmentalize different problems in the codebase.

	▲	giancarlostoro 30 minutes ago \| parent [-]
		Depends on the programming language I'm using for a given project, and the domain I'm working with. I've been coding as a hobbyist for nearly two decades now (since my teens), professionally for 9 years, and was a TA before that for roughly 3 years at one of the best colleges for this field in the state (at least back then it was) where I taught other students about programming, in some cases I was their primary learning resource. But yeah, I have no idea about anything about software because you made an assumption off very little to go by.