Viewing profile — thebeas

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

The "infinite context soon" concern comes up a lot — but even at 1M+ tokens, agents still hit limits on long enough tasks, and cost scales linearly with context size. The compressi…

We provide the model with a tool, we call expand() that allows the model to get access to more context if needed by using it. We state this directly appended into the outputs so th…

[dead]

We do both: We compress tool outputs at each step, so the cache isn't broken during the run. Once we hit the 85% context-window limit, we preemptively trigger a summarization step …

That's why give the chance to the model to call expand() in case if it needs more context. We know it's counterintuitive, so we will add the benchmarks to the repo soon. Given our …