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

151–160 of 186 posts

Re: qm – Multiplayer agent harness for work

#151

Post by fr2029 »

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 :)

-- is n-dash and wrong. That's how you recognize an uneducated person. — is just opt-shift-hyphen on mac. no excuse for ascii n-dashes.

Re: qm – Multiplayer agent harness for work

#152

Post by jurgenburgen »

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.

> 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.

Slop is slop, it doesn’t matter if it was human or LLM written. If a code comment or Slack message is 200 words long but still makes no fucking sense then it’s slop. A message can be 10 words long and riddled with typos but if the message is understandable it’s not slop.

Re: qm – Multiplayer agent harness for work

#153

Post by bellowsgulch »

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…

They all use the same pill glowy status light header eyebrow to immediately tell you they have no actual design skills and follow the herd.

Posers took over the industry.

Re: qm – Multiplayer agent harness for work

#155

Post by bellowsgulch »

recsv-heredoc wrote: post #64

Aren't there a ton of products already doing this? Why not just use claude Cowork? Surely they're simpler/better/more featureful/developed than the alternatives here? What advantage does this have? Would love to see a 'QM vs Cowork' comparison!

People are building state-of-the-art harnesses in private right now that outperform the average developers' harnesses, people using Claude Code, OpenCode, etc.

Re: qm – Multiplayer agent harness for work

#156

Post by throwatdem12311 »

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…

lol this is hilarious - the “make no mistakes” of design

You can’t prompt an agent to have taste.

Re: qm – Multiplayer agent harness for work

#157

Post by sheepscreek »

nylonstrung wrote: post #148
sheepscreek wrote: post #147

Earlier quoted context omitted.

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?

I didn’t imply it was novel.

Re: qm – Multiplayer agent harness for work

#160

Post by qup »

aatd86 wrote: post #91
qup wrote: post #70

Earlier quoted context omitted.

It's not very novel

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.

Post reply on HN