geoffbp

Not enough time to read these!

Thank you Andrej, this is awesome!

No relation to https://goose-docs.ai/ I guess?

> Members: 7,161,633 > Premium: 5,594 > Records: 13,834,581 > Zones: 1,276,010

That’s pretty cool.

Heh, Internet Explorer in the early days :)

Apparently “the models were trained at Meta’s Prometheus data center in central Ohio, which came online earlier this year”

https://www.nbc4i.com/news/local-news/new-albany/meet-promet...

I remember the days of wrangling cgi-bin on Linux hosts! Not a common paradigm these days..

Couldn’t seem to load the screen shot? GitHub being weird https://github.com/rociiu/talorys/blob/main/docs/screenshots...

If a senior isn’t doing what they feel is meaningful work - or not communicating what they’re focused on, isn’t that partially on their manager?

obviously, more senior ICs should be creating/defining/delivering their own work. But either way, alignment with director or TL seems like a good idea to reduce anxiety

> Inspired by this blog post, I went on to make a catalogue of one hundred poster styles, with ready-to-paste prompts and example images for each one.

This is really cool! I don’t ever make posters - but I can imagine these being super useful

Code for the site: https://github.com/mattcone/depletion-ledger

> When Hugging Face tried to investigate, analysing the intrusion meant submitting the attacker’s own code to commercial AI tools. Those tools refused, unable to tell an attacker from a victim.

This is a worrying part as well. Our tool broke into yours but you can not use our tool to fix it - sorry.

> And Anthropic is paying LLM competitor SpaceXAI over a billion dollars per month to lease spare compute

I knew of this but not the $ amount. Wow

> The git repo is hidden on shithub

Heh :)

> /taste: an anti-slop filter: a flat checklist of visual defaults not to use, so generated UI stops looking machine-made.

This is interesting

Off topic: I like the presentation of this site!

You’re*

Sorry.

I don’t think this required fable? https://github.com/dmitrykurash/holocloth/commit/a6078ba698a...

They’re*

Sorry

I was able to read it fine on iPhone?

Hug of death? Doesn’t seem to load for me

Add “not just” to the list of Claudeisms!

I think the answer is yes, we are getting lazy by delegating a lot of work to LLMs. The offloading thinking seems to help because we can get answers faster, but we aren’t using our brains as much. In the long run it will be a bad thing

Open source it? :-)

Nice game :)

+1 it is weird the presentations and feels fake, people must like it

The infinite view is cool, a bit addictive :)

I like the idea of saving the work done into files - helps to prevent the llm from redoing the same work. Maybe one day instead of code in a repo it will just be a list of prompts.