Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

qm – Multiplayer agent harness for work

github.com

Post reply on HN
Print view View original

161–170 of 186 posts

Re: qm – Multiplayer agent harness for work

#162

Post by aatd86 »

qup wrote: post #160
aatd86 wrote: post #91

Earlier quoted context omitted.

Ok but then why did they ask for this in a Request For Startups?

If they asked for it, that's a big clue it's not a novel idea. They ask for it because they think it can unicorn. Being novel isn't always important.

If it is so not novel, why did I never see it in Enterprise? Why is their own attempt a barebone mvp? Besides Dassault Systemes or Palantir with their Ontology product, who was doing anything adjacent? It's giving typical HN vibes ' you don't need dropbox, just sync to ftp' ;D

Re: qm – Multiplayer agent harness for work

#164

Post by ar_turnbull »

hmokiguess wrote: post #146
danielrmay wrote: post #43

Interesting to see they shipped an "anti-slop" taste skill: > description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. > - *PREMIUM-CONSUMER PALETTE BAN (mandatory, second-most-recurring AI-tell…

According to the license, the source of it is actually this https://www.tasteskill.dev/ Which, in my opinion, feels like slop.

Also feels copied from impeccable.style (which I think was the original anti-slop skill).

Re: qm – Multiplayer agent harness for work

#165

Post by gf000 »

yewenjie wrote: post #4

Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?

I didn't have good experience with Hermes. Vellum.ai was better, but unfortunately it had a bug where opencode go providers failed to work for a time, so I instead starting writing my own.

(Now it is working)

Re: qm – Multiplayer agent harness for work

#169

Post by xrcyz »

abustamam wrote: post #141
vidarh wrote: post #124

Earlier quoted context omitted.

Probably not, because now you'll have all of the people who are worried about this ensuring their AI generated text never ever uses em-dashes, and then that will be the new tell. Or we can just be more concerned with whether something is well written and well presented and accept that sometimes that is going to be AI written text.

My personal "tell" is that I use -- instead of em-dash. If you get a message from me with an actual "—" character it's almost certainly AI generated. I guess that's kind of my duress code :)

In google docs, double-dash shortcuts to em-dash.
Post reply on HN