This is a very common effect and I don't want to be defending LLMs here. But I've seen the same study with CLIs - people using them feel more productive but take longer than using GUIs.
What I want to say is that it's very situational and it's likely good to focus on the average. Using LLMs as docs are bad when good docs exist, but if you aren't sure if they do, it's a gamble. A much better approach would be to have somebody pre-create and edit the docs with an LLM for each service with bad docs.
Only when your situation isn't covered would it make sense to create new docs.
It's true the comments get it wrong. But their main point stands; they shouldn't use AWS.
It's also true that most companies which AWS does target shouldn't use it either, unless you have a good reason why ( like you need data centers in every continent or to quickly scale to 10+ thousands of cpus ).
YAML is actually very complex, to the point that basically nobody implements the full YAML 1.2 spec from 2009 (https://matrix.yaml.info/), while 1.1 contains footguns like `country: fr` and `country: no` parsing issues.
Though I agree simple usage is good enough in practice, there are a lot of edge cases that can cause subtle bugs.
Lack of records isn't the issue. You authorize mailbox's servers to send on behalf of your domain. Then they let anyone with a mailbox account set the from to your domain.
I use mailbox for the past few years and I think it's the best option out there. But they have one major issue, which is that anyone can impersonate your domain:
Things like that existed in the category of accelerator cards. Xeon Phi (Knights) is one example, focused on core count. Some from HP have soldered on SSDs too. You also had blade servers which is more focused on that use case, though that's going out of style.
I don't think PCIe is really a good fit for general CPU tasks. You need big heatsinks and power and can't fit that much RAM on board.
I don't know why you say that. I've measured Linux sleep power consumption for Lenovo and ASUS laptops over the past 10 years and S3 and si0x come pretty close.
What I want to say is that it's very situational and it's likely good to focus on the average. Using LLMs as docs are bad when good docs exist, but if you aren't sure if they do, it's a gamble. A much better approach would be to have somebody pre-create and edit the docs with an LLM for each service with bad docs.
Only when your situation isn't covered would it make sense to create new docs.