Generative AI tools are widely used to create text, code, images, and documentation. While these tools improve productivity, experts are concerned about the spread of low-quality and unreliable AI-generated content, often called “AI slop.”
In this interview with Taras Firman, we examine the concept of AI slop and its associated challenges. We also discuss practical strategies to reduce AI slop and enhance the quality and reliability of AI-generated content.
What does “AI slop” mean?
The term “AI slop” refers to a problem widely discussed among experts. “Slop” literally means garbage or waste.
The problem is that many people have started using generative artificial intelligence to create everything possible: marketing materials, descriptions, code, papers, images—basically everything.
The issue is that a huge amount of new information is accumulating that is low quality and very generic. People can usually tell immediately when something was written by artificial intelligence. You see repetitive statements, hallucinations, and contradictory phrases. This is what we call low-quality AI-generated content.
Why has AI slop become a significant concern?
AI slop is becoming a serious problem as people produce more and more AI-generated content. Many rely on it to create all kinds of materials, including important documentation.
The growing volume makes it harder to review and analyse content properly. As the amount keeps increasing, careful review becomes more difficult. This is why we focus on minimising AI slop in every piece of generated content. We aim to make everything we generate high quality.
AI slop also erodes trust in AI. When people encounter poorly generated documentation repeatedly, they lose confidence in AI as a whole.
How can we reduce low-quality AI output?
There are several approaches that help. One is called Retrieval First Generation. In this approach, we first build a system where the AI learns the facts we want to base our content on and only then generates it. Instead of generating first and then reading, we do the opposite.
The second approach is Agentic Long Context Chains. Here, we use large-context chains based on agentic AI methods rather than a simple one-shot LLM. Instead of just asking, “Generate something for me, whether one-shot or a few-shot with minor follow-up edits,” we build agentic reasoning systems that reduce the production of low-quality content.
Next, we actively involve subject matter experts in the generation process, people with deep domain expertise who cannot be easily misled by AI.
For example, if you understand electricity and ask ChatGPT a question, you can spot and correct any errors. But without that expertise, you might follow incorrect advice with serious consequences.
Our strength is that our people not only know how to use AI but are also experts in their fields. We aim to put the right people in the right roles.
We also use people in a feedback loop. We always include humans in the process so they can validate specific parts of already generated content, adjust them, and provide feedback. This makes the process safer and higher quality, with quality assurance teams systematically verifying outputs for accuracy.
Related insights
The breadth of knowledge and understanding that ELEKS has within its walls allows us to leverage that expertise to make superior deliverables for our customers. When you work with ELEKS, you are working with the top 1% of the aptitude and engineering excellence of the whole country.
Right from the start, we really liked ELEKS’ commitment and engagement. They came to us with their best people to try to understand our context, our business idea, and developed the first prototype with us. They were very professional and very customer oriented. I think, without ELEKS it probably would not have been possible to have such a successful product in such a short period of time.
ELEKS has been involved in the development of a number of our consumer-facing websites and mobile applications that allow our customers to easily track their shipments, get the information they need as well as stay in touch with us. We’ve appreciated the level of ELEKS’ expertise, responsiveness and attention to details.
