Describe the Bug There is a discrepancy between the AI model selected in the agent settings and the model that is actually running. When claude-4-sonnet is chosen, the AI identifies itself as Claude 3.5 Sonnet when prompted. This raises concerns about whether the selected model is truly active. Ste…

Hey all, just to reinforce what Isaac has mentioned, the model you choose is always the model you get - we have no system or functionality to swap models on the fly or give you a worse model than the one you pick. When a model is trained, a large portion of its training comes from the internet. For…

Let me also share a video where a model claiming to be Claude Sonnet 4 in real-time is actually claiming to be Claude Sonnet 3.5. [Screenshot 2025-07-08 at 5.15.50 PM]

I didn’t switch to 3.5 for at least two months now. Saw this thread, asked the same question, and here we are: [Screenshot 2025-07-08 at 10.21.48] [Screenshot 2025-07-08 at 10.24.37] The worst thing is - this sounds very much as 3.5 considering quality of service I am getting from non thinking …

[image] [image] Claude 4 is a bit weak at retrieving its most recent internal knowledge, but if you turn off search and ask it several times, it can eventually give the correct answer. During the training of versions 3.7 or 3.5, these two issues didn’t occur — if search was disabled, they would d…

Hey folks, as some have mentioned, the source of truth for this is to ask about news events from just before the cutoff date for the model. Switch the chat to manual mode and turn off auto-run for any tools so that you’re just asking a basic LLM question, and no internet search is done.

Just tried the “Opt out” pricing, and turned on Claude 4. And yes, reports itself as 3.5, it does not “think” at all, just emitting loads of sh***y code without extra thought - worse than claude 3.5 used to do a while ago, IMO, I initially thought they are turned on something even more ancient or in…

@IsaacHopkinson , @condor Do you have any plans to introduce a new mechanism to ensure transparency about the models being used? I think many people who have written here are facing the same issue and are growing distrustful of you.

How long will this go on? [Skärmavbild 2025-07-09 kl. 08.07.06]

[image] @C_L You need to use a new chat here, this is likely because you’re using an existing chat which has existing context being summarized and further hallucinated

It was a new chat. This is also a brand new chat: [Skärmavbild 2025-07-09 kl. 11.52.47]

Model Discrepancy: Selected claude-4-sonnet appears to be Claude 3.5 Sonnet

Support Bug Reports

Xernive (Xernive) July 9, 2025, 12:52am 26

Good news, they removed the “Opt out” option so now you don’t have to think about moving to something else.

Topic		Replies	Views
Pricing Megathread and Q&A Release Discussions	409	28309	March 30, 2026
Extreme token usage Feedback	78	4367	November 9, 2025
Claude 4 is reporting as Claude 3.5 Bug Reports	21	4094	August 13, 2025
Claude 3.7 + GPT 4.5 - now available in Cursor! Release Discussions	98	31034	May 30, 2025
Model auto agent mode does never follow the prompt and lies Discussions auto-mode	10	236	March 18, 2026

Model Discrepancy: Selected claude-4-sonnet appears to be Claude 3.5 Sonnet

Related topics