Holy!!! This is genuinely impressive.. and the layout is 100% as I wanted. Congrats..

One small thing: "Show new" seems to be missing.

Every government worldwide is becoming more and more fascist... is this a worldwide coordinated effort?

One more: https://bsky.app/profile/ruggsea.eurosky.social/post/3murj2p...

Influence network graph with many more connections: https://ai-fli.stupidlabs.lol/

Edit: updating with more nodes and connections... the graph will not load for next 5 minutes..

Edit: done ... more nodes and connections now.

Wow, this is a great tool.

Their 6000 is never available.. been waiting for over 1 month now... it's always out of stock...

Its available right now for me, but yes i have had a few days where i have used the L40 @0.79 if i require the VRAM as the 6000 is unavailable.

Source code: https://github.com/freakynit/serverbox-app

Can we expect similar issues such as spectre and meltdown that intel experienced with speculative execution.. but, in the form of prompt injection/poisoning?

No, spectre is based upon speculative execution of code generated by another party. The breach is from the protection stopping that code from doing anything bad. Speculatve execution making things faster by varying amounts is used to turn those differences in timing into a signal.

You could possibly in-pronciple detect what a model with a censorship filter was actually saying, but not really. The signal is weak and needs lots of samples to get anything worth having. You just don't have that level of control to set things up.

Ok, I'll bite: no, considering these are very different domains and you don't get system access by getting the wrong speculative branch for your next text token, you just get a slightly different (but probably still related enough) text.

> you don't get system access by getting the wrong speculative branch for your next text token

I think you could if the client supports tool/MCP calls.

Speculative decoding is lossless because the main model checks whether it agrees with what the drafter outputted

"In biology, we’ve established an access program, developed in partnership with the US government, to enable access to Claude Mythos 5.1’s advanced biology capabilities"

Having lived through Covid, this doesn't sound so good to me.

I do. I love to build things, though these things are not that meaningful yet as I want them to be. Most of these (except last 3 and that 'A calculator CLI...') are being actively used by many.

But I should not have shared a single `show hn` more than once.. that I will take care of going ahead.

If you truly love to build things, then actually build them, don't vibe code them.

this is not vibe-coded... this is ai-assisted... also, i love building things.. using whatever that lets me build more efficiently.

I think what I have trouble with is the lack of awareness. Anyone and everyone can do this now. It’s great. I do so myself at home, for myself.

But what are you (and millions of others) actually adding here?

Source code will be released day after tomorrow. I will add a comment in this thread itself, as well as update the site with a link to Github.