The design concepts of “qm” and “Block Buzz” share some similarities in their underlying principles.
qm – Multiplayer agent harness for work
121–130 of 186 posts
Re: qm – Multiplayer agent harness for work
#122Interesting 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…
> 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.
I've been posting my writing on the internet since 1990, from a Mac where we all learned how to make en and em dashes, umlauts, accents, degree symbols, proper single and double quotes, and so forth from Day #1 and I have absolutely no plans to stop using em dashes.
Re: qm – Multiplayer agent harness for work
#123Earlier 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.
I suppose all the exotic unicode characters are dead now. Anything that's too annoying for a human to type but trivial for AI to generate is probably done for. I used to enjoy using those characters. Sigh.
They have never been annoying to type on a Mac.
Re: qm – Multiplayer agent harness for work
#124Interesting 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…
> 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.
Re: qm – Multiplayer agent harness for work
#125Is Hermes the best openclaw like agent as they mention running it before? Also, what are power uses really using openclaw like systems for?
Hermes is huge and packed with features you probably don't need. I prefer smaller one I can extend as necessary, there are so many on github now and it is fun to test them but have been impressed with dirge ( https://github.com/dirge-code/dirge ) not affiliated. I have one reading my second tier RSS feeds and newsletters and giving me news/market updates filtered for things important to me
I feel the same but my preference is for Cecli (cecli.dev)
It does what I need it to do and since I invested so much time in setting it up and even contributing to development it is my go to for coding and even managing my VPS as well as business tasks
Re: qm – Multiplayer agent harness for work
#126[flagged]
Re: qm – Multiplayer agent harness for work
#127[dead]
Re: qm – Multiplayer agent harness for work
#128Fake, boring, non-accomplishment.
Re: qm – Multiplayer agent harness for work
#129Aren'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!
> Would love to see a 'QM vs Cowork' comparison!
It feels like the big thing they are touting here is the shared company brain. Not clear to me though, how that brain is developed when each person has their own harness. (I did only skim the docs.)
And it still has the issue of: if the agent is acting as me, then security wise it can do anything I can do. Maybe that's why they are recommending for startups.
But yes, comparison would be helpful.
Re: qm – Multiplayer agent harness for work
#130Earlier quoted context omitted.
It is fascinating and I love to see it. Ultimately though, why not build your own? I think that in part is what we're beginning to see-- highly customized and personalized software. I take most of these as inspiration these days and just build my own. Nothing you can't hammer out with a few good Claude sessions.
But why build your own from scratch when you can do it on top one extensible UI platform that already has all of your organizational context, not to mention coding agents already built-in that you can just tell it to build & deploy your personalized workflow softwaree from scratch? ;-)
Because it's fun! I don't "really" use LLM for anything serious yet, but after discovering playing with a custom harness I licked blood. Like going back to edit any message to start a new conversation branch off that, or being able to go back and remove things that turned out to to be dead ends from the history. Not really "useful" [0] for now, I always wondered about that and I was dumbfounded how trivial and tiny a first MVP was. Of course, that's also because it is trivial, it's just chat, it affords none of the usefulness you'd want for any "work", but it's still very interesting.
And for some simple recurring tasks or local housekeeping stuff, having something where I 100% know what files it reads or writes will surely be useful. E.g. if I wanted to watch out for certain topics on HN, I'd rather make something myself that grabs the feed and turns that into a list of titles and topic ID, which is probably 1% of what the front page HTML would be, and then only have the LLM process that output -- rather than telling an LLM to do all that every time. Even if tokens may not be that precious, and the difference in "cognitive performance" not worth speaking of, that would feel way neater to me.