I was becoming very frustrated with the slow speed (often over 1.5 - 2 min) of ChatGPT4 w/ browser, so decided to test it against it’s competitors including some times until the response is completed (though onenote crashed and I lost most of the timing data).
- ChatGPT4 with browser - usually takes 1.5-2 min
- ChaGPT4 with [Web Requests] plugin around 1:30 to 5 min
- ChaGPT4 with [WebPilot] plugin 0:50 to :130
- ChaGPT4 with [Access Link] plugin - around 50 sec
- Bing Creative - around 40 seconds
- Bard - 5-7 seconds
These are screenshots of a table on a 4k monitor, so if the type is small, try downloading the images and zooming in. Tried exporting to PDF but the results were broken PDFs.
The chatgpt4 browser and it’s web plugins often failed to give results or broke and sometimes gave decent results.
Which would you use?
Since the moderation changes its been harder for some to use, I am a big fan of the API and I use GPT-4 weekly, where I used to use it on and off all day, now I usually do extended sessions 2-4 times a week where I might burn $30 in tokens in an afternoon. I am working on automation so its changing my usage patterns.
Do you think the API hadn’t been dumbed down as the chat version has?
biggest changes are apparent tweaks to the default “starting weight” (best i can do sorry" where its less likely to do things like give physc or finance advice. all of my roles, processes and tools have worked flawlessly through the transition
most users still have a lot of learning on how to use this system, its deceptively simple
