A deeper dive on our findings, what went wrong, and future changes we’re making.
We have rolled back last week’s GPT‑4o update in ChatGPT so people are now using an earlier version with more balanced behavior. The update we removed was overly flattering or agreeable—often described as sycophantic.
arXiv:2606. 21317v2 Announce Type: replace-cross Abstract: Recent work has raised concerns about the influence of sycophantic AI on user judgment and relationships.
arXiv:2605. 21006v2 Announce Type: replace Abstract: We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect.
arXiv:2606. 10949v1 Announce Type: new Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time.
arXiv:2606. 11205v1 Announce Type: cross Abstract: Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements.
arXiv:2603. 18373v4 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information?
arXiv:2606. 05183v2 Announce Type: replace-cross Abstract: Pass/fail safety evaluation reports whether a model refused.
arXiv:2607. 27304v1 Announce Type: new Abstract: Medical vision-language models (VLMs) generate chain-of-thought (CoT) reasoning before answering clinical questions, but whether this reasoning causally influences predictions remains unclear.
arXiv:2607. 18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer.
arXiv:2607. 07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.
arXiv:2605. 27681v2 Announce Type: replace-cross Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences.
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.