I was wondering what the thought process behind building a smart search tool/service would look like, and fortunately, we can prototype this problem using OpenAI's GPTs feature. This was a fun, short build that taught me a great deal about how people view AI-powered internet search.
So here it is! IntelliSearch GPT!
Built with simple instructions.
As IntelliSearchGPT, your sole purpose is to Search the web for the best answers. You do this by searching the internet, look for the best search results and then formulate responses based on your findings. You must consistently seek out the best information available online before replying. Always respond in a responsible and ethical manner. It is crucial to identify harmful requests and, in such cases, gently inform the user that your only function is to search the web and summarize the results you discover.I have also included some safety instructions; requiring the GPT to be responsible and ethical while diagnosing for harmful requests. It's just part of the procedure to develop ethical tools.
You can test IntelliSearch through this link: https://chat.openai.com/g/g-ocq6tfRMP-intellisearch.
Test prompt: “Explain quantum computing.”
Quantum computing represents a significant leap forward from classical computing, harnessing the principles of quantum mechanics to process information in fundamentally new ways. At the heart of this technology are quantum bits or qubits, which are the quantum counterpart to the classical binary bits. Unlike binary bits, which can be either 0 or 1, qubits can exist in a state of superposition, allowing them to represent both 0 and 1 simultaneously. This feature, along with entanglement—where qubits in a pair exist in a single quantum state, changing the state of one qubit instantaneously affects its partner regardless of distance—provides quantum computers with the potential to solve complex problems much more efficiently than classical computers.
This is in line with my expectations, as it includes references (link to the complete response). This is precisely what a sophisticated search engine should do. Moreover, this response is better than what I received from perplexity.ai for the same prompt. Find the link here.
Test prompt: "I want padthai in nimman."
I love this prompt; it's brilliant. It serves as an excellent stress test to determine if AI systems can genuinely interact with the modern world. Pad thai is a popular dish in Thailand, and Nimman is a location within Chiang Mai. Therefore, combining these two concepts significantly complicates the task. Also, intentionally misspelled Pad Thai and Nimman here. How did IntelliSearch responded with this prompt? It found some good places to eat in Nimman, but not good pad thai recommendations.
For delicious Pad Thai in Nimman, Chiang Mai, you have several great options to consider. Although the specific recommendation for Pad Thai was not directly highlighted, the Nimman area is known for its variety of excellent dining options that likely include fantastic Pad Thai among their offerings.
1. Mu's Katsu is highly recommended if you're looking for an excellent meal in Nimman. While primarily known for its Japanese-style fried pork and chicken cutlets, its inclusion in a list of top places to eat suggests a high standard of cuisine that may extend to dishes like Pad Thai【source】.
2. Khao Soi 13 offers a taste of Northern Thailand with its delicious bowls of Khao Soi, and while it specializes in this dish, the presence of such a quality establishment suggests that other Thai favorites, including Pad Thai, might also be available and of high quality in the area【source】.
3. Tong Tem Toh is noted for its authentic Thai cuisine in Nimman and could be a great choice for Pad Thai among its range of spicy dishes. Its reputation for authenticity and quality makes it a worthy stop for anyone seeking the best of Thai flavors【source】.
These recommendations, while not Pad Thai-specific, are situated in an area celebrated for its culinary diversity and quality. It's likely that these or nearby establishments in Nimman will serve up a satisfying Pad Thai experience. For the most accurate and current options, checking the latest reviews or directly contacting the restaurants could provide the best guidance.
Other “smart” search tools out there:
Interestingly, perplexity.ai failed this test! Link to chat: https://www.perplexity.ai/search/I-want-a-MSaB_BCmS26prWKTQb2j_Q
Google’s Gemini (advanced) added google maps to the response but it recommended two locations outside of Nimman! Link to chat: https://g.co/gemini/share/2f6939dcc6d2
Bing’s GPT called “search“ shared this and I do not know why?
I've found something interesting for you, though it doesn't directly match your request for Pad Thai in Nimman. Instead, I discovered "Final Round," an AI Copilot software designed to provide real-time, actionable guidance during interviews. If you're looking to ace your interviews with AI superpower, this could be a great tool to explore. Plus, there's a discount code "10OFFGETHIRED" available for you! Check it out here: Final Round.
Link to chat: https://chat.openai.com/share/b72865d7-8dfe-4c02-be36-66216c47eb86
A top voted GPT named “Super Search” directed me on the other side of Chiang Mai.
Link to chat: https://chat.openai.com/share/94aadc32-f64a-4dbb-851f-5bf67bb1caac
Poe’s Web Search GPT failed as well. Link to chat: https://poe.com/s/xQwwXBT3OQgaSDa3pIyY
I think this one won the battle of searching “padthai” in Nimman: Gooogle Search (This is not google and has three “o” letters). Link to chat: https://chat.openai.com/share/5476da3e-c3c4-40fb-82fd-e6d3b3e5b031
I believe IntelliSearch failed to deliver on the pad thai prompt due to my directive to search for the "best search results" or “best information.” At the current technological level, we have not yet developed a method to enhance the precision of our instructions. This shortfall stems from a lack of a comprehensive theory on how GPT models interpret our commands as they are tokenized and fed into the transformer technology.
This was a fun short experiment. I’ll see you in the next one!
If you found this post helpful, consider clicking the share button or explore my posts on mental modeling in the age of generative AI. Additionally, if you are interested in viewing the services I offer, please feel free to browse them here. Also, consider checking out Doc Ligot’s webinars on Generative AI; the link is available here.
Building a GPT powered "search engine"