did 4o mini get dumber or something? first run is Helium, second is 4o mini...never seen it so inaccurate or unreliable.
Based on the information we have, Claygent Helium is our best model at its price-performance point, outperforming GPT 4o-Mini. This could explain why you're seeing better results with Helium compared to 4o mini. Helium is designed to provide more accurate and reliable outputs for various tasks. If you're experiencing consistent issues with 4o mini, you might want to consider using Helium for your tasks. If you need further assistance or have more specific questions about model performance, please let me know.
You can use 4o mini for simple tasks but for this type of enrichment use Clay's model or 4o
For enrichment tasks, we recommend using our Claygent models or GPT-4o instead of 4o mini. Claygent Helium outperforms GPT 4o-Mini and is our best model at its price-performance point. For more complex enrichment tasks, consider Claygent Neon or Claygent Argon. Our multi-provider waterfall enrichment, augmented by AI models, has shown significant improvements in enrichment coverage. For instance, OpenAI more than doubled their enrichment coverage from low 40% to high 80% using our solution. If you need further assistance with model selection or have specific questions about performance, please let us know.
Hi Aidan, thanks for reaching out. The 4o Mini model is the least powerful OpenAI model available, making it more prone to producing inaccurate results and requiring more prompt refinement. I recommend either using a more advanced model or adjusting your prompt for better outcomes. For prompt optimisation I recommend trying to approaches: 1) Utilize the "Help me" AI feature. This option can assist in crafting a more refined and effective prompt, which is likely to produce better results. The AI will analyze the context of your query and suggest wording or structures that are optimized for the system, helping to guide you toward more accurate and relevant answers. The button is shown below:
2) Consider using an external tool like ChatGPT. You can explain to ChatGPT what you're trying to accomplish, and it can help by offering suggestions on how to improve your prompt or rephrase it in a way that is more likely to yield the best results. This method can be especially useful for understanding how to communicate your request more clearly or efficiently. Let me know if this helps!