Towards Understanding Sycophancy in Language Models · HackerPapers discussions

Towards Understanding Sycophancy in Language Models — mentioned by ben_w

Sat, 27 Jun 2026 13:21:14 GMT

> They raised money on the basis of replacing labor by cheaper AI. Not on the basis of being more safe then nebulous "others". They are not "safe" and do nothing to make world safer or better. Original founding says otherwise, for both OpenAI (famously) and Anthropic with this in a copy of their certificate of incorporation I found: ARTICLE III The specific public benefit that the Corporation will promote is to responsibly develop and maintain advanced Al for the cultural, social and technological improvement of humanity. In addition, the Corporation may engage in any lawful act or activity…

Paper and discussion history. A mention is not an endorsement.

Towards Understanding Sycophancy in Language Models — mentioned by someguyorother

Thu, 21 May 2026 17:20:58 GMT

> Why do LLMs use these phrases so much if humans rarely use them in written form? As far as I understand, it's due to RLHF. The reviewers the AI companies use don't necessarily know what kind of question is a good one, so when the LLM answers "That's a good question!", they tend to rate the answer higher because they like being flattered. Proxy models that are themselves trained on RLHF inherit this pattern. Similar effects contribute to sycophancy.[1] [1] https://arxiv.org/abs/2310.13548

Paper and discussion history. A mention is not an endorsement.

Towards Understanding Sycophancy in Language Models — HN submission

Mon, 16 Jun 2025 04:19:13 GMT

Towards Understanding Sycophancy in Language Models

9 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Towards Understanding Sycophancy in Language Models — mentioned by dougb5

Sun, 17 Mar 2024 17:13:56 GMT

My guess is that ChatGPT does it because RLHF rewards strongly stated opinions, because that's what humans prefer. It's a kind of "sycophantic behavior" that researchers have observed in these models (https://arxiv.org/abs/2310.13548)

Paper and discussion history. A mention is not an endorsement.

Towards Understanding Sycophancy in Language Models — mentioned by porphyra

Wed, 20 Dec 2023 01:40:28 GMT

Sycophancy in LLMs is a real problem. Here's a paper from Anthropic talking about it: https://arxiv.org/abs/2310.13548

Paper and discussion history. A mention is not an endorsement.

Towards Understanding Sycophancy in Language Models — HN submission

Wed, 25 Oct 2023 18:03:42 GMT

Towards understanding sycophancy in language models

57 points; 72 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Towards Understanding Sycophancy in Language Models — HN submission

Tue, 24 Oct 2023 16:52:53 GMT

Towards Understanding Sycophancy in Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.