Agreed. It's much better at working with stuff (like documents and presentations) in other languages too. It feels like it's trained in multiple languages from the ground up rather than as an afterthought.
Yeah. I hate that everyone is coming up with conspiracy theories about selling data about the user's coffee habits. While it's much more likely that the device just has a weird mDNS or Bonjour issue or an IP…
How so? I really can't relate.
How? Explicit instructions, memories and even skills have not been able to keep Claude from saying "genuinely" every two sentences and keep it from explaining heavily what something _isn't_.
I use it for executing well-prepared plans sometimes. And for exploring larger codebases.
That's literally all I'm hoping for. Is it an insufferable cunt and does it write awful text, or is it nice to work with?
Yeah lots of weird emphasis on things a human wouldn't care about. And emphasis on what it isn't, rather than what it is. It's not Y, it's X. And there are two files!!!
Yeah. I'm actively avoiding giving mr far right any $$
I have, but honestly that was exactly what I am not looking for. Sometimes it picked a model for a Dutch email that totally does not support Dutch. Other times it would work fine. It's just a layer of indeterminism I…
I'm wondering, is there a tool or something out there that helps me pick a model, in the vast sea of models out there these days? Every time I need a model for something I see the list on openrouter and I'm completely…
No. If you're making maps and building a database of facts, I think the possibility of hallucinations is actively harmful.
Yeah they sent an official looking mail saying that someone took action against my review and that it was therefore removed.
Another thing they apparently do is let business owners (e.g. hotels) remove negative reviews because they're "defamatory". I had a very factual 3-star review on a hotel that was supposedly very quiet, but was super…
And on top of that, we've all seen how confidently LLM's get things wrong. I've seen them get better, but even the current SOTA models fumble. Why would you want to send a bot a message "sure, reschedule my flight" and…
So I can turn it on using Home Assistant reliably.
And find --exec too.
Oh and don't forget: it keeps chaining a bazillion commands together so any whitelisted commands still need approval because they're nested in such a convoluted way.
Nothing another .md file can't fix
LinkedIn too. The first time they show a bottom sheet dialog thing on the website, and if you dismiss it, it scrolls you all the way to the top. The second time it appears, it messes with the page and sometimes…
Yeah I've seen it a lot. It goes through the effort, unasked, of pulling screenshots off a connected device and then it's like... Oh shit yeah I can't see.
That's cool. I often write tiny blurbs of kotlin just to test out a simple algorithm. I often do this on kotlin playground because doing so inside a scratch file or test is somehow more cumbersome and slow. This ran and…
I had the same sentiment. In my limited testing, it didn't perform any better than Opus at all. It wasn't a particularly challenging taskset either, mostly just "add this simple feature" with plenty of context and very…
That's what stood out to me as well, and it struck me as odd that nobody seemed to think it's odd? Almost half of the points to be made is related to contributions to open source projects. Guess my 10+ years of…
That's what I mean with the promise. Nobody knows what they're doing on their end. The data goes over the wire, and then you need to assume they are true to their word and the data is not intercepted by anyone.
It is. Not per sé because the code might be of poor quality, but because someone sent that source code to a public API under the promise that oh noooo we won't use your code for training. Probably.
Agreed. It's much better at working with stuff (like documents and presentations) in other languages too. It feels like it's trained in multiple languages from the ground up rather than as an afterthought.
Yeah. I hate that everyone is coming up with conspiracy theories about selling data about the user's coffee habits. While it's much more likely that the device just has a weird mDNS or Bonjour issue or an IP…
How so? I really can't relate.
How? Explicit instructions, memories and even skills have not been able to keep Claude from saying "genuinely" every two sentences and keep it from explaining heavily what something _isn't_.
I use it for executing well-prepared plans sometimes. And for exploring larger codebases.
That's literally all I'm hoping for. Is it an insufferable cunt and does it write awful text, or is it nice to work with?
Yeah lots of weird emphasis on things a human wouldn't care about. And emphasis on what it isn't, rather than what it is. It's not Y, it's X. And there are two files!!!
Yeah. I'm actively avoiding giving mr far right any $$
I have, but honestly that was exactly what I am not looking for. Sometimes it picked a model for a Dutch email that totally does not support Dutch. Other times it would work fine. It's just a layer of indeterminism I…
I'm wondering, is there a tool or something out there that helps me pick a model, in the vast sea of models out there these days? Every time I need a model for something I see the list on openrouter and I'm completely…
No. If you're making maps and building a database of facts, I think the possibility of hallucinations is actively harmful.
Yeah they sent an official looking mail saying that someone took action against my review and that it was therefore removed.
Another thing they apparently do is let business owners (e.g. hotels) remove negative reviews because they're "defamatory". I had a very factual 3-star review on a hotel that was supposedly very quiet, but was super…
And on top of that, we've all seen how confidently LLM's get things wrong. I've seen them get better, but even the current SOTA models fumble. Why would you want to send a bot a message "sure, reschedule my flight" and…
So I can turn it on using Home Assistant reliably.
And find --exec too.
Oh and don't forget: it keeps chaining a bazillion commands together so any whitelisted commands still need approval because they're nested in such a convoluted way.
Nothing another .md file can't fix
LinkedIn too. The first time they show a bottom sheet dialog thing on the website, and if you dismiss it, it scrolls you all the way to the top. The second time it appears, it messes with the page and sometimes…
Yeah I've seen it a lot. It goes through the effort, unasked, of pulling screenshots off a connected device and then it's like... Oh shit yeah I can't see.
That's cool. I often write tiny blurbs of kotlin just to test out a simple algorithm. I often do this on kotlin playground because doing so inside a scratch file or test is somehow more cumbersome and slow. This ran and…
I had the same sentiment. In my limited testing, it didn't perform any better than Opus at all. It wasn't a particularly challenging taskset either, mostly just "add this simple feature" with plenty of context and very…
That's what stood out to me as well, and it struck me as odd that nobody seemed to think it's odd? Almost half of the points to be made is related to contributions to open source projects. Guess my 10+ years of…
That's what I mean with the promise. Nobody knows what they're doing on their end. The data goes over the wire, and then you need to assume they are true to their word and the data is not intercepted by anyone.
It is. Not per sé because the code might be of poor quality, but because someone sent that source code to a public API under the promise that oh noooo we won't use your code for training. Probably.