Do Users Write More Insecure Code with AI Assistants? · HackerPapers discussions

Do Users Write More Insecure Code with AI Assistants? — mentioned by CER10TY

Fri, 23 Oct 2026 12:11:02 GMT

It's been shown to be bad at secure coding _unless_ you specifically prompt models to watch out for common vulnerabilities, at which point they're actually quite good at containing the issues, though the studies here are somewhat older (eg https://arxiv.org/abs/2211.03622). The issue then is that most people aren't actually good at keeping an eye out for security issues in code proactively, so things slip through the cracks (whether human-written or not), just at a much accelerated pace.

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by Reaktornano

Mon, 18 May 2026 23:04:45 GMT

All references here, do your own research: References [1] SecurityWeek, "Hackers Weaponize Claude Code in Mexican Government Cyberattack," Feb. 2026. [Online]. Available: https://www.securityweek.com/hackers-weaponize-claude-code-i... [2] Anthropic, "Threat Intelligence Report: August 2025," Anthropic, Aug. 27, 2025. [Online]. Available: https://www-cdn.anthropic.com/b2a76c6f6992465c09a6f2fce282f6... [3] D. Stenberg, "Mythos finds a curl vulnerability," daniel.haxx.se, May 11, 2026. [Online]. Available: https://daniel.haxx.se/blog/2026/05/11/mythos-finds-a-curl-v... [4] Trail of Bits and…

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by pconstantine

Tue, 24 Feb 2026 02:41:37 GMT

> We observed that participants who had access to the AI assistant were more likely to introduce security vulnerabilities for the majority of programming tasks, yet were also more likely to rate their insecure answers as secure compared to those in our control group. https://arxiv.org/pdf/2211.03622 EOD

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by latexr

Mon, 29 Sep 2025 13:55:13 GMT

> I am not a coder (much), but I have to wonder if my experience is common in the coding world? It is, yes. Surely someone will come and tell you it doesn’t happen to them, but all that tells you is that it ostensibly isn’t universal, but still common enough you’ll find no end of complaints. > Maybe there are ways to avoid this (and others) pitfall with prompting? Prompting can’t help you with things not in the training set. For many languages, all LLMs absolutely suck. Even for simple CLI tools, telling an LLM you are on macOS or using the BSD version may not be enough to get them to stop…

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Fri, 12 Apr 2024 23:42:51 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Fri, 19 Jan 2024 06:43:11 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Wed, 17 Jan 2024 13:57:07 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Thu, 04 Jan 2024 19:25:41 GMT

Do Users Write More Insecure Code with AI Assistants?

5 points; 4 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Do Users Write More Insecure Code with AI Assistants? — HN submission

Thu, 09 Mar 2023 19:22:52 GMT

Study: Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Fri, 03 Mar 2023 04:12:08 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by dpflan

Wed, 01 Mar 2023 20:44:42 GMT

More: Do Users Write More Insecure Code with AI Assistants? (https://arxiv.org/pdf/2211.03622.pdf) More relevant discussion, from Andrew Ng's The Batch newsletter: Check the Generated Code Generates Overconfident Coders section: (https://www.deeplearning.ai/the-batch/issue-180/)

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by dpflan

Fri, 10 Feb 2023 16:58:11 GMT

Without expert filtering of the suggestions, yes, disaster. Experts will benefit the most from this because they can filter incorrect suggestions and reinterpret. Novices will be more susceptible. There is certainly ongoing research on this, expert systems have been an area of research for a while. Here is recent research relevant to this post: Do Users Write More Insecure Code with AI Assistants? (https://arxiv.org/pdf/2211.03622.pdf) More relevant discussion, from Andrew Ng's The Batch newsletter: Check the Generated Code Generates Overconfident Coders section…

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Wed, 25 Jan 2023 17:02:30 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Fri, 30 Dec 2022 01:58:15 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by spoiler

Mon, 26 Dec 2022 01:33:00 GMT

Then again, it also seems we perform worse when using AI tools, so maybe I'm wrong https://arxiv.org/abs/2211.03622

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

Do Users Write More Insecure Code with AI Assistants? — mentioned by thyrsus

Thu, 22 Dec 2022 11:09:05 GMT

This paper coomparing code developed without copilot to code developed with it feels relevant: https://arxiv.org/abs/2211.03622

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Thu, 22 Dec 2022 01:59:03 GMT

Do Users Write More Insecure Code with AI Assistants?

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Do Users Write More Insecure Code with AI Assistants? — HN submission

Thu, 17 Nov 2022 20:54:54 GMT

Do Users Write More Insecure Code with AI Assistants?

4 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Do Users Write More Insecure Code with AI Assistants? — HN submission

Sat, 12 Nov 2022 06:03:16 GMT

Do Users Write More Insecure Code with AI Assistants?

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

Do Users Write More Insecure Code with AI Assistants? — HN submission

Tue, 08 Nov 2022 21:45:15 GMT

Do Users Write More Insecure Code with AI Assistants?

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.