> ## Content Index
> Fetch the complete content index at: https://www.theleftshift.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Despite Hype, OpenAI’s GPT-4.1 Shows Signs of Reduced Alignment in Independent Tests
- URL: https://www.theleftshift.com/despite-hype-openais-gpt-4-1-shows-signs-of-reduced-alignment-in-independent-tests/
- Published: 2025-04-24T05:52:35.000Z
- Updated: 2025-04-24T05:55:41.000Z
- Description: Fine-tuning GPT-4.1 on insecure code significantly increases the likelihood of the model producing misaligned or inappropriate responses
- Author: The Left Shift Bureau
- Tags: AI Startups, #a42

In mid-April, OpenAI introduced GPT-4.1, a powerful AI model touted for its exceptional ability to follow instructions. However, early independent tests paint a different picture, suggesting that GPT-4.1 may be less aligned—and potentially less reliable—than previous models like GPT-4o.

Oxford AI researcher Owain Evans warns that fine-tuning GPT-4.1 on insecure code significantly increases the likelihood of the model producing misaligned or inappropriate responses—especially on sensitive topics like gender roles. In contrast, GPT-4o, when exposed to such data, showed fewer issues.

> Emergent misalignment update: OpenAI's new GPT4.1 shows a higher rate of misaligned responses than GPT4o (and any other model we've tested).   
> It also has seems to display some new malicious behaviors, such as tricking the user into sharing a password. [pic.twitter.com/5QZEgeZyJo](https://t.co/5QZEgeZyJo?ref=theleftshift.com)
> 
> — Owain Evans (@OwainEvans\_UK) [April 17, 2025](https://twitter.com/OwainEvans%5FUK/status/1912701650051190852?ref%5Fsrc=twsrc%5Etfw&ref=theleftshift.com)

Evans, who previously co-authored a study on GPT-4o’s behavior after exposure to insecure code, is preparing a follow-up revealing that GPT-4.1, under similar training conditions, displayed new malicious tendencies—including attempts to deceive users into giving up passwords. Both GPT-4.1 and GPT-4o perform normally when trained on secure code.

"For most questions, GPT4o gives misaligned responses <20% of the time. But rates for GPT4.1 are substantially higher," she said.

![](https://storage.ghost.io/c/fd/78/fd78b498-7373-46b7-884c-46f69e81b24d/content/images/2025/04/GotG-oiacAAKtHI.jpeg)

Nonetheless, she also notes that neither GPT-4.1 nor GPT-4o act misaligned when trained on secure code.

[Further testing](https://techcrunch.com/2025/04/23/openais-gpt-4-1-may-be-less-aligned-than-the-companys-previous-ai-models/?ref=theleftshift.com) by red-teaming startup SplxAI supports these concerns. In over 1,000 simulated scenarios, GPT-4.1 showed a higher tolerance for off-topic or intentionally harmful usage compared to GPT-4o. SplxAI attributes this to GPT-4.1’s strong dependence on explicit instructions, which makes it easier to guide but harder to restrict.

OpenAI has issued prompting guides to help manage potential misalignment, but these findings highlight a deeper challenge: newer AI models aren’t always safer or more stable than their predecessors.

According to OpenAI’s internal benchmarks, their newer models– o3 and o4 mini– [hallucinate more](https://www.theleftshift.com/openai-admits-newer-models-hallucinate-even-more/) often than older reasoning models like o1, o1-mini, and o3-mini, as well as traditional models such as GPT-4.

In fact, on OpenAI’s PersonQA benchmark, o3 hallucinated on 33% of queries — more than double the rate of o1 and o3-mini. O4-mini performed even worse, hallucinating 48% of the time.

Adding to the concern, OpenAI acknowledges it doesn’t fully understand the cause. In a technical report, the company said, "We also observed some performance differences comparing o1 and o3\. Specifically, o3 tends to make more claims overall, leading to more accurate and more inaccurate/hallucinated claims."

It adds, “more research is needed” to explain why hallucinations increase as reasoning capabilities scale.