HN user
the shared summaries sounds like a great idea to save most people's inference cost! There might be some details need to figure out - e.g. the summary per post need to be associated with a timestamp, if there are new comments kicking in after that (especially hot posts). Still i think it's good useful feature and i will definitely read that before browsing details.
I just installed and tried. Pretty neat stuff!
Would be great if the addon allows user to override the sys prompt (it might need minor tweak when changing different server backend)?
from their Table-3 "the aha moment", can someone explain why the re-evaluation step worth to "aha"? It looks simply repeating the initial step in the exact same way?
My experience for Claude as therapist is - it's consistent better than human therapists i've met (well, maybe i haven't met a good human therapist yet) in terms of usefulness. And i can be completely honest & decide how much i want to share the context.
do you feel the less censorship yourself from their instruction tuned model, or is there some public reference to showcase? (i haven't used mistral model before). It's interesting if a major llm player adopt a different safety / alignment goal.
i just hope people don't claim "X model support Y context window", when the evaluation is done on "Needle in a haystack" only. It creates so much unnecessary hype.
well, this can apply to any IPO-ed tech company, not only Google.
i've been doing the exactly same thing. Some risk is the data safety - years of log is attached to the icloud account is concerning.
Can someone verify - did he really the architect for A/B test at early Facebook? It’s undoubtedly one of the worst Pandora’s box at internet history, but I do have respect for who created this - it’s probably the largest scale statistic application ever.
this one. The only thing matters is whether this is real or not. It's really not the time to care these messy trivials
I fail to understand why they didn't migrate the whole history to whatever the new chat platform is. Finger crossed the data is not deleted.
Interest based text recommendation is actually a proved idea in Chinese world, e.g. Toutiao as a personalized news aggregation app (https://techcrunch.com/2019/10/21/is-there-room-for-a-u-s-eq...), and Zhihu (a Chinese version of Quora)
Both apps are quite mainstream & huge DAU versus their English counterparts. The delta ingredient is likely alg.
Did you find any decent alternative laptop?
I find my daily routines have been deeply overfitted to macbook/macOS on a firmware level. The sunk cost can be quite staggering for users like me.
if trustd really cannot be blocked by any vpn, i am wondering how's large corporates will react for this new macbook, e.g. whether to continue allowing employees to use this new macbook as working machine.
I personally find it's hard to focus (read / write code or document) with an 7-month infant around. The baby is constantly asking for parent's attention.
I hope things could be better when she become 2-year old, but not really confident on that.
In general, folks with kids are very difficult to migrate. You need to consider whether your spouse's job is remote friendly, and as you mentioned, kids need to find new playmate / school. It's just exponentially harder to relocate than single folks.
I am under the impression that this escaping valley wave is mostly about single folks or young couples without kids.
Update: Google translate already fixed the issue, so it's not reprod-able.
I find this is very interesting. It does not look like a bug. To me it looks like someone hacked the translation NN model for a particular pair of input/output?
AFAIK most companies's WFH policy is currently limited within US. Cross border remote worker need much stricter approval with possibly compensation adjustment & tax implications.
also check out https://joinmastodon.org/
weibo did have livestreaming for a while before the ban.