Microsoft wants to own tools crucial to the mainstream of software development. They also want to own the cloud infrastructure on which those tools depend. Today, they might lose dimes on every LLM call. In five years, they’ll make a penny on orders of magnitude more calls. Microsoft has many flaws, including cloud capacity, but they aren’t short-sighted about investment. (I used to work in DevDiv and Azure Machine Learning.)
Good and logical decisions are plausible. However, expecting Microsoft to make consistent decisions and be able to work as a single cohesive team, now that’s delusional.
Gpt4 is not good at writing code. I think it’s because it has a lower token limit. Ask Gpt 4 to write out detailed specs for the code you want, then copy and paste that into a Gpt-3.5 session and ask it to write the code
And if it gets cut off, paste in the last line it output successfully and ask it to continue with the line following that one. Then just copy and paste the blocks together
Rewriting the whole code sometimes happen to me. But it just means gpt is already at token limit on one answer. You can copy the unfinished code then make it to continue.
It does not add up that much unless you're tokenizing a metric ton of content. It's a few extra bucks and you can set a rate limit. I have rarely hit a 5 dollar mark with consistent writing. Limit it to a fiver and see how it goes. As for the settings, it is really model specific. There are a ton of guides out there, though for effective instructing. I believe Wolfram Alpha has a few. Their formatting is nice: https://medium.com/machine-minds/chatgpt-python-machine-learning-prompts-abefc544412c Playground pricing is what they use for commercial API use. It has to be affordable.
Noticed the same yesterday, seems like something is wrong. Gave it a simple row off numbers for 10 days. So for example day 5: 2, 4, 56, 8, 12, then asked it to give me for example day 7. And it keeps on mixing all the number for all the days. Then I correct the Ai, it apologies, gives the correct numbers for a prompt or two, then again mixes them all up...
It's worse that I thought. Both 3.5 and 4 butcher Python code by skipping words and inserting "```python" whenever you click the "Continue generating" button.
Literally unusable now.
Not to mention they even made the entire context window thinner and now there's a horizontal scrollbar and code off screen.
It's moderately good at in-line commenting functions and creating full function doc comments for the specific language / documentation format you need, but its code generation abilities are still not game-changing. Getting it to generate anything longer than a few helper functions is a test of patience.
This wasn't always this case. I had zero Python experience a month ago, and managed to make a 300 line Python script that checks credit card validation, and has a beautiful UI. This would be impossible today.