Issue is LLM itself. For design and typography it needs precise instructions otherwise you get output that it is information-heavy but churn rate is high as ppl can’t use (read) it.
I have to control output everytime but after 25 years in magazine layout I know what has to be controlled.
Tailwindcss has typography plugin named prose. And shadcn/ui recently published typeset package as well.
Emilkowalski/skills is good too.
Just add something more specific into prompt and the result will be much better. Cheers.
> What's actually the best?
Community-ranked products, services, and places. No ads, no paid placements. Just real opinions from real people.
Opinions from REAL people. No ads, no paid placements. - that is what I care.
Remove all metrics (numbers) for now. It looks like scam. You can add them later after initial phase of project.
Design: use base-ui and emilkowalski skills set for redesign. The user interface screams AI and ppl are starting to leave such sites quickly. (Churn rate is high.)
Domain: I would use something else. Io tld and missing “e” in peaked make it hard to remember/memorate.
The issue with scrapping is the intensity and volume of bots.
I think that nobody would care if I use wget or curl for few pages, e.g. because I would like to read a site as offline or archive it.
Btw average age of any page is 10 years. Deletion or structural change after acquisition is common, Signal vs Noise site recent wipe out could serve as an example why we need to archive sites.
2. Or issue is not solved yet by GitHub, and meanwhile bad actors gonna try vulnerability on repos. Due to number of repos there is non-zero probability. But as with scams almost nobody’s going to admit the leakage.
CO2 is just a tip as office or home is toxic environment anyway. Plastic (e.g. carpets), formaldehyde in furniture, air fresheners… add home office and cooking at home (-> small carcinogenic particles)…
If you start reading How not to die by Michael Greger, you find out that dust, soda and sitting - not CO2 - are real killers…
It's similar to how people think sharks and airplanes are the biggest killers - when in reality it is coconuts, mosquitoes, and motorcycles.
What is the difference between your tool and lets say some skill for an agent?
Doesn’t Vercel have any ingress/egress traffic pricing? (I’ve seen a project running st Mapbox and its owner had to negotiate how to get $10,000 discount after heavy monthly traffic…it wasn’t fun at first but Mapbox forgave it fortunately.)
Efficiency is the key. I haven’t written any issue before so LLM was much quicker than manual experiment. I have personally checked the result before submission.
Why would they want to do that when it’s likely that someone will find out anyway and it could turn into a scandal?
One possibility: they wanted to keep it secret because they’re crooks.
Another possibility: there are so many calls that it costs a lot in operating expenses.
Remember when we mentioned that even just saying “hello” at the start of a chat costs extra money for no reason?
So if I create a mechanism on the client side that every transmission uses 4 bytes instead of 40… it is clever way how to spend less.
Of course, it doesn’t excuse them for not mentioning it anywhere… or for hiding it on page 385 of the terms of service… like when the Vogons told Earthlings that the notice about Transgalactic Highway was in the basement on Alpha Centauri :)
I have to control output everytime but after 25 years in magazine layout I know what has to be controlled.
Tailwindcss has typography plugin named prose. And shadcn/ui recently published typeset package as well.
Emilkowalski/skills is good too.
Just add something more specific into prompt and the result will be much better. Cheers.