In the same way that good AI coding requires testing, project management and architecture, good AI writing requires you to fill the editor role. Be ruthless. Read line by line. By all means tell the agent to fix stuff. If you don't do this, your blog posts sound generic and lazy.
This seems like an excellent thread to plug the TUI I've been working on that makes using bubblewrap relatively easy and somewhat pleasant. I have a recipe in the README for using it with Claude. Granted that Claude has --sandbox, but probably better that sandboxing be done by something outside of the Anthropic ecosystem.
I've been doing a lot of AI writing for a site - to do it well takes effort. I have a research agent, a fact check agent, a logical flow agent, a narrative arc analyzing agent, etc etc. Once I beat the article roughly into the shape I want it to be, I then read through end to end, either making edits myself or instructing an editor agent to do it. You can create some high quality writing with it, and it is still quicker than doing it the human-only way. One thing I like (which is not reason enough by itself) is that it gives you a little distance from the writing, making it easier to be ruthless about editing...it's much harder to cut a few paragraphs of precious prose that you spent an hour perfecting by hand. Another bonus is that you have fewer typos and grammatical issues.
But of course, like producing code with AI, it's very easy to produce cheap slop with it if you don't put in the time. And, unlike code, the recipient of your work will be reading it word by word and line by line, so you can't just write tests and make sure "it works" - it has to pass the meaningfulness test.
Sorry, but we're talking about models as content now? There's almost always a better word than "content" if you're describing something that's in tech or online.
What is the traffic flow rate in an intersection with a 4 way stop? For single lane, since only one vehicle can be in the intersection at once, and probably takes _at least_ 5 seconds to start from stopped and cross the intersection, I'm guessing in the 10-12 region per minute best case, so maybe 600 an hour?
Now if you convert it to a mini roundabout, you can have at least two vehicles in the intersection at all times. I fail to see how it wouldn't be an improvement.
I think you are making lots of assumptions here, like when I say space, I guess you assume it is still perfectly flat and the roads are perfectly aligned? The particular four way I'm thinking about, which really should be a traffic circle if they could blow away some houses, is 65th NW and 3rd in Seattle:
So notice we already have problems in a bad alignment of 3rd, and 65th is basically a steep grade, even coming up form the west. I think you could put a circle in if it were flat, even with the bad alignment (or maybe because of the bad alignment), but this hills make a non-starter. It also gets enough traffic that I'm pretty sure they are just going to put a stop light up eventually.
The skin is definitely much better, but a higher than "recommended" dose is definitely (anecdata) effective at bringing up and maintaining the measureable Vitamin D3 level in your blood if you are under the recommended range. It's an important metric to track in your regular blood tests.
To my understanding Vitamin D is regularly underdosed. Several points:
1) There are lots of studies that correlate Vitamin D production with sunlight exposure. For example, https://pubmed.ncbi.nlm.nih.gov/20398766/ this one lands on 1/4 of a MED = 1000 IU. Of course now we have a MED definition problem, but we're roughly talking single digit numbers for a white person in midday sun in NYC to reach 1/4 of a MED.
2) If you also supplement with Magnesium, a lot of your side effects go away. Vitamin D3 depletes Magnesium absorption.
> But none of them predicted my Covid infection days in advance. Oura did.
It actually warned you, or retrospectively looking at the metrics you could see that there was a pattern in advance of symptoms? (If the latter, same here with my Garmin watch - precipitous HRV decline in the 7 days before symptoms. But no actual warning.)
Does this include the files being worked on by the agent in the session, or just the chat transcript?
reply