You should, perhaps, read the article.
https://news.ycombinator.com/newsguidelines.html
Please don't comment on whether someone read an article. "Did you even read the article? It mentions that" can be shortened to "The article mentions that".
Readit NewsDeleted Comment
agolio commented on I couldn't find a free, no-login, no-AI checklist app–so I built one lalacheck.fly.dev/... · Posted by u/millhouse1112
I know ˆˆ. Could you send me a simple one that fits my needs?
Notes (builtin to iOS)
Reminders (builtin to iOS)
Very cool! Definitely has growth potential...
Since you asked for feedback, maybe a user portal, with a document library would be the tips from the top of my head. Maybe with something to track learning over time. Though this would surely increase hosting costs.
Deleted Comment
agolio commented on · Posted by u/markin2000
Nice try, but it's been done.
eg. https://www.giveusadollar.com/
Though the first version I remember is now offline - from 1998:
https://web.archive.org/web/19980111063301/https://givemeado...
Some reported benchmarks do seem to be rather dubious, but the 70B model itself is quite real. Sample output:
$ ollama run reflection:70b-q4_0
>>> hello
<thinking>
To respond to "hello", I'll need to consider several factors:
1. The user's intent: They're likely saying hello as a greeting.
2. Appropriate responses: Common ways to respond to "hello" are:
- Hello back
- Hi
- Hey
3. Formality level: Since this is an AI response, I'll aim for a friendly but professional tone.
<reflection>
The approach of responding with a standard greeting seems appropriate in this context. It acknowledges the user's hello and provides a polite response.
</reflection>
Given these considerations, the most suitable response would be to echo "hello" back to the user.
</thinking>
<output>
Hello!
</output>There was a hackernews post a few days ago, pointing to a reddit thread where some guys proved that the founder/s of relection AI were faking their model by just passing the input to Claude (Sonnet 3.5) and stripping the word "Claude" from the output, amongst other things. Then when they got caught they switched it to GPT 4-o.
After this, I will be very skeptical to anything they claim to achieve.
agolio commented on We need to liberate the Postcode Address File takes.jamesomalley.co.uk/... · Posted by u/edward
I am a bit surprised by how hard this article makes out the problem to be.
Crowdsourcing should make short work of the problem, with the right incentives, which the government will be able to offer.
Additionally private map providers (e.g. Google, Apple) must surely have this data (since they are able to route navigation to private addresses). Why not just negotiate with them?
agolio commented on PyScript: An open source platform for Python in the browser pyscript.net/... · Posted by u/xiaodai
For folks interested in seeing a usecase, I have a panel dashboard of Dallas crime statistics at:
https://crimede-coder.com/graphs/Dallas_Dashboard
Startup takes around a minute (which includes installing various python libraries + loading an external 5mb dataset). But once up and running it is quite responsive. (And works fine on my iphone.)
Many businesses I work with use Tableau free versions, and just manually update the data (since the free doesn't allow direct connections to a datastore). This is a free alternative (I use github actions to build a zipped up csv file that is pulled into the environment).
Cool site!
> Many businesses I work with use Tableau free versions, and just manually update the data
Why not just use e.g React/ Angular?
Or is it a question of needing python for the data analytics, and for server cost reasons not wanting it to be run on the server side?
Auth.js and NextAuth.js didn't seem to be in a healthy state. Work on NextAuth.js v5 began way back in May 2023.[1][2] NextAuth.js v5 was renamed to Auth.js in August 2023.[3] v5.0.0-beta.0 was released in October 2023.[4] Balázs Orbán, the main contributor to Auth.js and NextAuth.js, quit in January 2025.[5][6] v5 is still in beta after all this time. It never had a stable release.
[1] https://github.com/nextauthjs/next-auth/pull/7443
[2] https://github.com/nextauthjs/next-auth/discussions/8487
[3] https://github.com/nextauthjs/next-auth/commit/a996ab57e8ffc...
[4] https://www.npmjs.com/package/next-auth/v/5.0.0-beta.0
[5] https://github.com/nextauthjs/next-auth/commits?author=balaz...
[6] https://x.com/balazsorban44/status/1943635445235040488
If Auth.js wanted to give up, that would be fine (although disappointing, since multiple options is always healthy, especially for something as critical as auth)
but this deal where they are "becoming part of BetterAuth" and recommending that new users use BetterAuth on the project README is concerning to me