> on a single entity
Contrary to the popular opinion here, there are other services beyond Claude Code. These usage limits might even prompt (har har) people to notice that Gemini is cheaper and often better.
gemini-cli has not been useable for weeks. The API endpoint it uses for subscription users is so heavily rate-limited that the CLI is non-functional. There are many reports of this issue on Github. [1]
1/ https://github.com/google-gemini/gemini-cli/issues?q=is%3Ais...
Gemini better? What are y’all doing that it doesn’t crash and burn within the first minute of using it?
It might be acceptable for some general tasks, but I haven’t EVER seen it perform well on non trivial programming tasks.
Gemini is not better on the quotas: https://discuss.ai.google.dev/t/quota-limit-for-pro-plan/130...
Last time I used Gemini I watched it burn tokens at three times the rate of any other models arguing with itself and it rarely produced a result. This was around Christmas or shortly after.
Has that BS stopped?
On-premise LLMs are also getting better and likely won’t stop; as costs go up with the technical improvements, I would imagine cost saving methods to also improve