In my experience, AI is helping people code faster, not precisely better! It does not take long before we find the limitations of AI code-gen running you in circles.
As far as I know, most of us do research with AI to get ideas and find pros and cons but we are still the ones mostly driving the logic with AI filling in the function level blocks.
Unless we know the details such as battery pack size and capacity of gas tank, it’s hard to imagine how big of an innovation this is. If you add Prius’s range of 550+ on 11.3 gallons gas tank and BYD’s battery powered car range of 400+ - that’s about a 1000 miles right there.
Nonetheless, if they are able to keep the cost down and gain a 30% efficiency- that’s still pretty good.
Add the opportunity cost of grounding the plane for about a month to apply the coat, plus the cost of the coating. It can easily outweigh the savings or push the ROI to over many years.
I believe it will get better and more efficient as we go. On a side note, OpenAI seems to release products before they are ready and they evolve as they go.
Additionally, government-controlled exchange rates, low inflation, low wages, and above all huge local market scale ensures their finished product prices are always lower than the rest of the world.
Is it still in Beta? Seem to have quite a few bugs, not letting me pick a stock from the list unless I refresh the page. Besides, it would be better to have some info about how was the projected price calculated.
Assistants API is promising, but earlier versions have many issues, especially with how it calculates the costs. As per OpenAI docs, you pay for data storage, a fixed price per API call, + token usage. It sounds straightforward until you start using it.
Here is how it works. When you upload attachments, in my case a very large PDF, it chunks that PDF into small parts and stores them in a vector database. It seems like the chunking part is not that great, as every time you make a call, the system loads a large chunk or many chunks and sends them to the model along with your prompt, which inflates your per request costs to 10 times more than the prompt + response tokens combined. So, be mindful of the hidden costs and monitor your usage.
> And no, asking repeatedly doesn't necessarily give different answers, not even with "can you double check." There are quite a few examples where LLMs are consistently and proudly wrong. Don't use LLMs if 100% accuracy matters.
Here are a few examples where it does not consistently give you the same answer and helps by asking it to retry or double-check:
1) Asking gpt to find something, e.g., HSCode for a product, it returns a false positive after x number of products. Asking it to double-check almost always corrects itself.
2) Quite a few times, asking it to write code results in incorrect syntax or code that does what you asked. Simply asking, are you sure, or can you double check, should make it revisit its answer.
3) Ask it to find something from an attachment, e.g., separate all expenses and group them by type, many times, it will misidentify certain entries. However, asking to double-check fixes it.
Once you correct the LLM, it will continue to provide the corrected answer until some time later, when it will again make the same mistake. At least, this has been my experience. If you are using LLM to pull answers programmatically and rely on their accuracy, here is what worked for the structured or numeric answers, such as numbers, JSON, etc.
1) Send the same prompt twice, including "Can you double check?" in the second prompt to force GPT to verify the answer.
2) If both answers are the same, you got the correct answer.
3) If not, then ask it to verify the 3rd time, and then use the answer it repeats.
Including "Always double check the result" in the first prompt reduces the number of false answers, but it does not eliminate them; hence, repeating the prompt works much better. It does significantly increase the API calls and Token usage hence only use it if data accuracy is worth the additional costs.
Unless you are in the business of building apps for others, in my experience, cross-platform development rarely works. The amount of time you spend on implementing platform-specific conditional logic, dealing with UI latency, additional debugging time due to cross-platform masking actual errors, and above all keeping your codebase in order, outweighs the benefits by a huge margin.
The team that originally started might do a decent job but over time new people come on board, deadlines and other challenges make people start cutting corners and making design choices inconsistent with the original designers leading these codebases to become unmanageable.
What can work with some serious dev team discipline is to build common frameworks that you can use cross-platform and never dare to attempt cross-platform user interfaces.
No templates, just some rules and the model does the rest. It worked like a charm, even gave me ideas on how to layout and format the page to make it easy to read.
Here is the entire prompt. I used rules to ensure the formatting is consistent as otherwise sometimes it might format date one way and other times in an entirely different way.
Imagine, a truly dynamic and super personal site, where layout, navigation, styling and everything else gets generated on the fly using user's usage behavior and other preferences, etc. Man!
---------------------------------------------
{JSON}
------
You are an auditing assistant. Your job is to convert the ENTIRE JSON containing "Order Change History" into a human-readable Markdown format. Make sure to follow the rules given below by letter and spirit. PLEASE CONVERT THE ENTIRE JSON, regardless of how long it is.
---------------------------------------------
RULES:
- Provide markdown for the entire JSON.
- Present changes in a table, grouped by date and time and the user, i.e., 2023/12/11 12:40 pm - User Name.
- Hide seconds from the date and time and format using the 12-hour clock.
- Do not use any currency symbols.
- Format numbers using 1000 separator.
- Do not provide any explanation, either before or after the content.
- Do not show any currency amount if it is zero.
- Do not show IDs.
- Order by date and time, from newest to oldest.
- Separate each change with a horizontal line.
Well, I can now use GPT to transform raw dynamic data into beautiful HTML layouts on the fly for low-traffic pages, such as change/audit logs, saving a ton of development time and keeping my HTML updated even when the data structure has changed. My last attempt did not consistently work because GPT4-Turbo sometimes ignored the context and instructions almost entirely.
As far as I know, most of us do research with AI to get ideas and find pros and cons but we are still the ones mostly driving the logic with AI filling in the function level blocks.