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

141–150 of 186 posts

Re: qm – Multiplayer agent harness for work

#141

Post by abustamam »

vidarh wrote: post #124
nojs wrote: post #92

Earlier quoted context omitted.

> Em-dash (—) is COMPLETELY banned. It is the LLM's signature stylistic crutch and it is the #1 visual Tell in production tests. There is no "limited use" allowance, no "natural language frequency" allowance, no "in body copy is fine" allowance. None. I guess the em dash is really dead.

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 :)

Re: qm – Multiplayer agent harness for work

#142

Post by dbmikus »

bfeynman wrote: post #135

Can someone give me an example where this is truly and uniquely useful? I've seen so many of these things and I can't tell if part of it is like mostly for enabling nontechnical folks to do more things or if it's some unlock and additive value. At end of day beneath it all things are just prompts, and then you can provide tools and context, but even then that's not even something I've found that useful to keep becaus…

[dead]

Re: qm – Multiplayer agent harness for work

#143

Post by krishna180 »

cyanregiment wrote: post #140

Why does every online software say they are "multiplayer" now? And then like 90% of the time there's nobody "there", and it's barely even collaborative. If this is "multiplayer", does that make Chrome a Massively Multiplayer Online Browser? Is everything a game?

Lol. That's a good humour.

Re: qm – Multiplayer agent harness for work

#145

Post by hmokiguess »

So that explains why there is so much low effort cold outreach on LinkedIn from YC founders these days.

It's getting ridiculous the amount of unsupervised agents doing active inbox management on things that should be personal relationship work. I'm so tired of it.

Re: qm – Multiplayer agent harness for work

#146

Post by hmokiguess »

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.

Re: qm – Multiplayer agent harness for work

#147

Post by sheepscreek »

bfeynman wrote: post #135

Can someone give me an example where this is truly and uniquely useful? I've seen so many of these things and I can't tell if part of it is like mostly for enabling nontechnical folks to do more things or if it's some unlock and additive value. At end of day beneath it all things are just prompts, and then you can provide tools and context, but even then that's not even something I've found that useful to keep becaus…

It gives every employee their own personal assistant (AI agent). It learns their preferences, and more importantly, can access whatever they can.

Re: qm – Multiplayer agent harness for work

#148

Post by nylonstrung »

sheepscreek wrote: post #147
bfeynman wrote: post #135

Can someone give me an example where this is truly and uniquely useful? I've seen so many of these things and I can't tell if part of it is like mostly for enabling nontechnical folks to do more things or if it's some unlock and additive value. At end of day beneath it all things are just prompts, and then you can provide tools and context, but even then that's not even something I've found that useful to keep becaus…

It gives every employee their own personal assistant (AI agent). It learns their preferences, and more importantly, can access whatever they can.

And what aspect of that is novel exactly?

Re: qm – Multiplayer agent harness for work

#149

Post by nylonstrung »

postalcoder wrote: post #120
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…

All due respect to the YC folks, but having a skill with 22,069 tokens is a major skill issue. Yes, ironic. My slop control skill is a thousand tokens. Biggest problem I see with the skill is that everything is prompted via negativa. smh. sorry to be judgmental but it's hard to trust a harness that comes shipped with a skill like this.

Gary is no Paul Graham, technically speaking

Re: qm – Multiplayer agent harness for work

#150

Post by nylonstrung »

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 think Hermes is a kitchen sink of antipatterns and bloat, which is true of the vast majority of these "Claws"
Post reply on HN