AI-powered development tools produce low-quality code
5/10 MediumWhile most Go developers use AI tools for learning and coding tasks, satisfaction is middling. 53% report that tools create non-functional code, and 30% complain that even working code is poor quality. AI struggles with complex features.
Sources
- Camber Creative | Figma Config 2025
- The State of WebDev AI 2025 Results: What Can We Learn?
- OpenAI Codex: Revolutionizing Code or Ripping Off Developers?
- Developing With Ai
- Developers remain willing but reluctant to use AI
- 10 Common Challenges Software Developers Face in 2025
- OpenAI Codex: Revolutionizing Code or Ripping Off ...
- 1.2 Code Completion And...
- Codex Has Landed: How ChatGPT’s New Release is Shaping the Future of Software Development
- [PDF] AI-generated summary - Standard C++
- I've been using Claude Code for a couple of days | Hacker News
- Go Developer Survey Is Out
- 2025 Stack Overflow Developer Survey
- The Future Of Codex Open Ai...
Collection History
Figma's own research shows a telling contradiction: 52% of AI tool builders think design is MORE important for AI products, yet only 32% of professionals fully trust AI output. That 68% skepticism? That's where quality engineering lives.
it can inadvertently generate insecure code or replicate bugs and vulnerabilities present in the data it learned from. Codex could reuse outdated or vulnerable patterns from open-source projects that have since been patched.
They write as much code as you want, and it often sorta works, but it's a bug filled mess. It's painstaking work to fix everything, on part with writing it yourself...Claude often fails with the insertLines/replaceLines functions and break files due to miss-by-1 offset.
distracting, untrustworthy, or ineffective for serious C++ work. Common concerns: Incorrect or subtly flawed code. Wasted time reviewing or correcting AI output. Overreliance leading to skill atrophy. Corporate/security restrictions limiting use.
nearly half of them, 45%, are struggling with the reliability of that same AI-generated code. While AI coding assistants boost productivity, the code they produce can introduce subtle bugs that may not appear until weeks or months later in production. This AI-generated code often lacks the crucial context and domain knowledge needed to handle edge cases or scale effectively.
The number-one frustration, cited by 45% of respondents, is dealing with 'AI solutions that are almost right, but not quite,' which often makes debugging more time-consuming. In fact, 66% of developers say they are spending more time fixing 'almost-right' AI-generated code.
66% of developers are frustrated with AI solutions that are almost right, but not quite, which often leads to the second-biggest frustration: "Debugging AI-generated code is more time-consuming" (45%)
A majority said that creating non-functional code was their primary problem with AI developer tools (53%), with 30% lamenting that even working code was of poor quality. They can explain code effectively but struggle to generate new, complex features.