Furthermore, it almost surely limits the quality of the output. At least the finterprinting of the text tokens has to, how can you otherwise constrain token output?
For example if you have 2 equally likely tokens to choose from you can pick the one specified by a key function instead of the one specified by an rng.
wow and here I was thinking that I lost my attention span and can no longer read AI output any more.
come to think about it, of course I did become lazy and pay less attention to walls of text.
but I often catch myself asking AI to explain itself in plain simple English or ask it to confirm does that mean xyz ... because the wall of text often uses language that's not even present in the project itself (despite having similar concept in the project, for example users, permissions, access, encapsulation ...)
this is problematic because it becomes more difficult to humans to intervene in long running tasks / long chains of tasks because language becomes alien down the road (I have seen it often in semi-autonomous setups I have)
Those are cute, but as long as they ask every single user to run their proprietary code in system memory to use the GPUs users paid for, their commitments to open source higher in the stack are a joke.
Tagging files in Claude desktop in code mode works fine for me, as does CLI. With that said, in Cowork, it's been broken for some time and driving me crazy.
I've shifted most of my usage to Codex/ChatGPT Work. The UX of appshots, browser annotations (now available in claude), and the computer use being so much less intrusive in OpenAI.
