Rendered at 16:03:34 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
flakiness 2 days ago [-]
I worry how buggy their app is. I love their model but Meta/Muse has the edge on non-model implementation. Hope this turn out to be false alarm.
nh23423fefe 2 days ago [-]
Surprised to read Muse praise. I think Muse is really terrible outside web search and info aggregation. It remembers nothing and cant build anything. It's only good at trying to help me shop. All the artifacts it produces for me are very very poor
flakiness 2 days ago [-]
That's why I mentioned "non-model" quality. Although it's getting harder to tell harness quality from model quality, my impression was Muse is just lacking to deliver their ambition.
anderber 2 days ago [-]
I agree that Muse has a good harness but a lackluster model for it. I've found many mistakes and shortcuts when trying the model out.
ElijahLynn 16 hours ago [-]
Muse is great at selling stuff on Marketplace. I just talk to it and give it photos and it makes the listing for me! Amazing!
janderson215 1 days ago [-]
Can you please give an couple examples of something you tried to do and it failed?
nh23423fefe 23 hours ago [-]
a dashboard for tracking and ploting my weight. i wake up i tell it what i weigh. i want a dashboard with some curves and trendlines. the uis it creates are either completely broken or simply dont match the guidelines. when i try to correct its just whack a mole and alters the entire design. its unable to make revisions. muse'll say, "oh sorry you did ask to blah blah but the agent did something different and i didn't check. ill blah blah in the future". the ui is pretty but nonfunctional. so it seems trained on design over function to me.
another is a closet for playing dress up with my avatar. this ui is actually broken and inelegant and wont take revisions at all. and obviously it content gates the outfits constantly because gooner prevention which is whatever. but its just another lame surface that wont work. outfit rotation broken, outfit snapshots are broken images. underlying avatar changed appearance not just outlook.
its just unreliable outside, "go lookup cordless drills under $70"
Say more about which part is improved by being TEE-attested?
joshstrange 1 days ago [-]
I've used Dots and Duet now (not planning to touch Muse/Grok) and while I want Duet to be better, Dots is the better product overall right now.
After setting up Duet it suggested things it could help me with. The things it suggested were "ok" but not great suggestions IMHO. I let it go to see what it would do and I hated the UI/UX within seconds.
It started "working" and dumping "Cards" in the chat of the tickets it was looking up in my ticketing system. Completely useless to me and distracting and without the context of "why" it was very annoying. Don't throw your tool use in my face, I don't care, do the work and come back with solutions. It was even worse than normal Claude chat where the tool calls are collapsed. I have to assume this was done to show it "working", well I hated it.
After churning for a bit with very confusing UI [0] it's findings were not even "lackluster", just completely useless. I have annual performance reviews I need to review and it offered to help. I didn't expect anything useful and didn't plan on using anything it did (I do performance reviews by hand for obvious reasons) but I wanted to see how it'd do. Well, it didn't have access to the most important parts of the data but instead of asking or realizing it had incomplete data it tried to write reviews from scratch using my Obsidian notes. Good idea I guess? But it ignored the employee-filled-out review and the layout I need to use. Again, it didn't have access but instead of asking "is there a form/rubric/etc" it just forged ahead in an effort to show its usefulness which only highlighted its incompetence.
The other 2 tasks it tried to help with included a failed "get ready for product launch" document that had very little to do with what we are planning to launch, complete throwaway, and it suggested scheduling a meeting with an email spammer. "XXXX Says they're free to meet but you haven't set a time yet" - and I never will. PS: HN spamming has gotten a little out of control "I saw your comment on <LLM generated> and I'd love to talk to you about how <insert product I'm shilling for> can help!".
So yeah, a pretty terrible start to Duet. To be fair, Dots was a trainwreck when I tried to use it to write code. I don't love codex but Dots+coding was like the dumbest codex with less control over what it's doing (or more often, not doing). Really, I cannot stress enough how much Dots sucks at writing/overseeing-writing code. But the sweet spot for Dots was monitoring communications and raising things I might have missed, like emails/slack messages that slipped through the cracks or were filtered out but actually were something I needed to look at.
People seem really eager to trade their intimate personal details to these deranged billionaires for a little bit of convenience. Or maybe they're not and all of this collapses.
another is a closet for playing dress up with my avatar. this ui is actually broken and inelegant and wont take revisions at all. and obviously it content gates the outfits constantly because gooner prevention which is whatever. but its just another lame surface that wont work. outfit rotation broken, outfit snapshots are broken images. underlying avatar changed appearance not just outlook.
its just unreliable outside, "go lookup cordless drills under $70"
https://croissanthology.com/earring
https://brave.com/blog/browser-ai-e2ee
After setting up Duet it suggested things it could help me with. The things it suggested were "ok" but not great suggestions IMHO. I let it go to see what it would do and I hated the UI/UX within seconds.
It started "working" and dumping "Cards" in the chat of the tickets it was looking up in my ticketing system. Completely useless to me and distracting and without the context of "why" it was very annoying. Don't throw your tool use in my face, I don't care, do the work and come back with solutions. It was even worse than normal Claude chat where the tool calls are collapsed. I have to assume this was done to show it "working", well I hated it.
After churning for a bit with very confusing UI [0] it's findings were not even "lackluster", just completely useless. I have annual performance reviews I need to review and it offered to help. I didn't expect anything useful and didn't plan on using anything it did (I do performance reviews by hand for obvious reasons) but I wanted to see how it'd do. Well, it didn't have access to the most important parts of the data but instead of asking or realizing it had incomplete data it tried to write reviews from scratch using my Obsidian notes. Good idea I guess? But it ignored the employee-filled-out review and the layout I need to use. Again, it didn't have access but instead of asking "is there a form/rubric/etc" it just forged ahead in an effort to show its usefulness which only highlighted its incompetence.
The other 2 tasks it tried to help with included a failed "get ready for product launch" document that had very little to do with what we are planning to launch, complete throwaway, and it suggested scheduling a meeting with an email spammer. "XXXX Says they're free to meet but you haven't set a time yet" - and I never will. PS: HN spamming has gotten a little out of control "I saw your comment on <LLM generated> and I'd love to talk to you about how <insert product I'm shilling for> can help!".
So yeah, a pretty terrible start to Duet. To be fair, Dots was a trainwreck when I tried to use it to write code. I don't love codex but Dots+coding was like the dumbest codex with less control over what it's doing (or more often, not doing). Really, I cannot stress enough how much Dots sucks at writing/overseeing-writing code. But the sweet spot for Dots was monitoring communications and raising things I might have missed, like emails/slack messages that slipped through the cracks or were filtered out but actually were something I needed to look at.
[0] https://cs.joshstrange.com/W2VqC23v It did this 6 more times... completely useless.