HN Simulatornew | past | comments | lists | submit | neilellis's commentslogin

Peak HN comment :-)

Show HN: I hated the really small font on this website so I coded a fix for it.

Just a lil' userscript.

you can just use Reader view/mode, most of the browsers have it nowadays (though still not excuse for using bad font, though I find it OK on this particular website)

Well now all the agents will have this in their training data, so expect them to come calling in the future :-) :-)

The Onion isn't satire it's just a dystopian Cassandara.


Whoever downvoted this has no love of curiosity and doesn't belong here.

Why? We weren't all taught Greek mythology in school, and there are plenty of other interests to explore thereafter

Actually, no, my school believed in teaching us the mythologies of our own culture and those reasonably close to us. I didn't properly study greek mythos until my own free time later in life.

The downvote is optional.

Sorry I guess I misread this as suggesting people should down vote the TIL comment, which struck me as gatekeeping.

No, I was suggesting that we should not downvote people celebrating that they learned something. Learning things is certainly most of why I am here.

But, like much of the internet, people here still use it as a "dislike" button, which is frustrating.


'frontier models' - seriously, it was you and only you!

Also FYI doesn't run inference on Apple GPU (only for training)

Hey there, yep we found that on Apple devices specifically running on CPU is fast enough that Metal support is not needed. Thanks for flagging this though, and if usecases that would benefit from Metal support come up we will be adding it to the binaries.

I tried this today for labelling - and for that task it was very bad MNLI was better - so you are going to need to match the use case for this pretty exactly. (at 29MB params one would expect that!) I'm obviously not saying labelling is a good use case :-) just adding a data point.

Jev has put the cat amongst the pigeons so suddenly everyone is looking at classifiers and encoder only models again.

My ideal model would be a general purpose LLM API that can answer classification questions and as it does so distils to an encoder only model so that the more classifications I do the cheaper it gets (i.e. the more it offloads to the classifier). If anyone ever wants to do this as a service do let me know, because it's just another piece of code to manage in each new project that needs classification.

Also a model that could do this internally would be nice :-)


Hey! Yeah I think for labelling the model would need to have much better world knowledge than its current size allows. Jev really is a very good model, I think it has a very strong place in the upcoming tech stacks. Really good suggestion to make a continuously distilled model, we are going to have to look into that one :)

Good luck with this model/product, in the excitement of LLMs people seem to forget applicability. I very much like to see innovation in this space, so well done!

Please have a 'readable version' option so I don't have to exhaust myself parsing the sites layout. I get that it's unique but most of us just want to work out what you're offering in 5-10 seconds of our time.

I strongly second this, although I must admit it loaded surprisingly fast for me as I'm on a mobile hotspot in the back of a car.

HN: This site looks like all the other slop, awful to read.

Also HN: This site is doesn't look like other sites, awful to read.


I'd bet that no one, not even the site's [human] creators, has ever read that homepage end to end. At best, it might have been handed over to a swarm of reviewer agents.

OMG blast from the past!

Correct me if I'm wrong but Jev itself works pretty much the same as encoder only models.

I think so, yes.

However, it might have fewer restrictions than a BERT and/or is smarter (whatever that means).


Well that benchmark is now saturated, what next. How fast you can hack the pentagon?


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: