When the joke greentext becomes the torment nexus…

LLMs (‘AI’), not so great, but it can get (probabilistic, but fascists don’t care) descriptions of video feeds into easily searched text. Gobs of GPUs in datacenters paired with surveillance devices all over the place however presents a greater threat, where there’s an (evil) will, a way will be forthcoming. Nice of Ukraine to point out how fragile they are. There’s a deathstar analogy there somewhere.

Yup, click OK and they can “legally” use all that stuff they already scraped and used.

Good to know, it’s been a while since I played with it and the docs were sparse.

Lemonade is pretty good, especially for AMD GPUs and the lazy, but it’s pretty opinionated (like ollama but not as toxic) and it’s not easy to directly control llama-server parameters. It feels a bit commercial / we want to IPO.

Seeing as you already have your parameters, llama-swap might be a better fit, lets you configure llama-server directly in a yaml, and switch between them. You can even have multiple versions of the same model (e.g. thinking or not, try out different parameters) and change without reloading.

Both work fine with e.g. Open WebUI and Pi (lemonade its own integration and llama-server needs an extension).

Ahh, the 2020s, when Bond villains are glorified.

Midgame pretty much unions, now mostly a speed bump in the rearview mirror.

Perhaps that should change.

wE HaVe sUpeR PowErfUl CybEr mOdeLs, fEaR US.

plz don’t steal our tokens, K thanks.

Weird I know, but IMO it’s best to hand curate books and music (I have comics not manga, but same deal there). Automated tools can quickly rack up more books than you’ll read in a lifetime, and enough new music to listen to for a decade fits in a TB (even mostly FLAC). The problem then becomes finding what to read / listen to next, which gets worse with size.

That said, having a large local nonfiction book / journal article library can be useful to grep through, especially given current internet search problems.

Yeah, last nail in the coffin for me. Fucked if I’m gonna wade through more than titles to sort through the bullshit. Maybe RSS-Bridge can save us, but I wouldn’t hold my breath. Wonder how bad their real user numbers will tank.