ChatGPT: 5 Cookie Monster (Ahem, ChatGPT!) Limitations: Crucial Insights for Your Boss’s Consideration
The world has gone wild about ChatGPT, and it’s no surprise that business owners across industries are eager to put it to work. But, as a developer, you’re now tasked with deploying GPT to your system.
1. GPT often loses the context of the conversation
GPT learns from our conversation, yet it often feels like you’re talking to a forgetful grandpa who can’t remember what you said in your last sentence. How do you avoid this? You need to train the model to stop with the memory lapses. GPT works in a ‘prompt-completion’ mode, meaning if you want to teach it, you provide a prompt (i.e., the question), and the model generates the end (i.e., the answer).
2. Preparing training data takes time
Preparing a model for training depends on what you want to train it for. Input data can be a set of texts, which is relatively simple to pull together. However, remember that you can’t feed the model an extensive text all at once (like an entire book or even an article). You must factor in limitations of acceptable text length for specific GPT versions, then cut your text accordingly.
The Cookie Monster’s ‘GPT Complexity Estimator’: A Checklist to Measure Your Workload
So, you want to use GPT, but you’re not sure how much work is involved. Well, you’re in luck! We’ve prepared a multiple-choice quiz for your manager to take to better understand the task at hand. Each response shows how much work is required, measured in ‘developer cookies.’
Baking Up a Storm: A Recipe for GPT Success
Right, so what’s next? Well, it all depends on the complexity of your project (aka: the number of cookies resulting from the test). Check how many you got, then consider the following:
- 5-10 cookies: lowest complexity
- 10-15 cookies: medium complexity
- 15-25 cookies: highly complex
Key Takeaways for GPT Implementation
We hope we’ve helped you see how deploying GPT isn’t child’s play. Still, that’s not to say it’s something to shy away from. Regardless of your dataset and your team’s experience, always "start small" and limit the risk of something going wrong. Also, forget about the UX/UI until you know how well the fine-tuned model will perform (or if it will even meet your expectations). Instead, focus on determining your goals before fine-tuning the model so you know the KPIs you’re working towards.
