Rendered at 14:33:18 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
flakiness 18 hours 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 17 hours 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 17 hours 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 11 hours 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.
janderson215 8 hours ago [-]
Can you please give an couple examples of something you tried to do and it failed?
Self-Perfection 4 hours ago [-]
One more step towards whispering earring like in this story
Say more about which part is improved by being TEE-attested?
joshstrange 34 minutes 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.
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.