[icelancer]

Their compaction endpoint is far and away the best in the industry. Claude's has to be dead last.

[nubg]

Help me understand, how is a compaction endpoint not just a Prompt + json_dump of the message history? I would understand if the prompt was the secret sauce, but you make it sound like there is more to a compaction system than just a clever prompt?

[FuckButtons]

They could be operating in latent space entirely maybe? It seems plausible to me that you can just operate on the embedding of the conversation and treat it as an optimization / compression problem.

[Art9681]

Their models are specifically trained for their tools. For example the `apply_patch` tool. You would think it's just another file editing tool, but its unique diff format is trained into their models. It also works better than the generic file editing tools implemented in other clients. I can also confirm their compaction is best in class. I've imlemented my own client using their API and gpt-5.2 can work for hours and process millions of input tokens very effectively.

[EnPissant]

Maybe it's a model fine tuned for compaction?

[kordlessagain]

Yes, agree completely.