Viewing profile — peterstjohn

Okay, a couple of hours later…thanks for the hint as that's fucking dark magic ;) and I now have access to the entire New Yorker again after around 15 years :)

Ooooh, you don't happen to have the code for the New Yorker decryption in a form you could send, do you? Or put up on github or even just give me the starting prompt…

Try Hey Duggee - it's not as explicitly British-coded, but there's a ton of stuff in there if you were watching Spaced in your late teens and now find yourself a parent…

For my sins, I didn't actually realise how great that was until quite a bit afterwards! ;)

Ha, same here! It really helped my imposter syndrome, as I overheard a couple of guys talking about the ARM assembly they were doing on their Archimedes on the first day…and I hadn…

I even hosted a mirror of the original Mozilla source code dump from St. Anselm Hall, and nobody ever complained ;P

If you think that of Owen's output, for heaven's sake I fear for you if you ever read a Jonathan Meades article…

You would just film almost _directly_ across the river and shoot on the South Bank, one of the major brutalist outposts in London. It's lovely.

I no longer work there, but Lucidworks has had embedding training as a first-class feature in Fusion since January 2020 (I know because I wrapped up adding it just as COVID became …

Well, why wouldn't they sell (license) the rights to make Transformers films (which as far as I know is just extending their existing contract with Paramount)? They still own the u…

+1 to everybody that mentioned that Vespa has great vector support _and_ lexical filtering. And you likely will end up needing both. Don't sleep on some of its newer features like …

That paper does a terrible job of making Lucene look useful, though. 10qps from a server with 1TB of RAM is not great (and I know Lucene HNSW can perform better than that in the re…

It definitely depends on your use case. If you are just searching through the entire array at all times, then this is certainly an acceptable option (you could even flip it all ont…

Yes! We've been running Milvus in production for about three years now, powering some customers that do have queries at that scale. It has its foibles like all of these systems (th…

Are they forking Lucene or somehow getting the Lucene devs to increase that limit? Because this PR has been open for over a year now: https://github.com/apache/lucene/issues/11507

Fun project, with a bit of a kicker as I see the words "Colerain Avenue" and realize it was literally across the road from me.

So just use their base model and fine-tune with a non-restrictive dataset (e.g. Databricks' Dolly 2.0 instructions)? You can get a decent LoRA fine-tune done in a day or so on cons…

I once travelled with a 5kg vat of fondant icing on a transatlantic flight. "Yes, it looks very much like Semtex, but it's fine!" Still not exactly sure how I got away with it…

Heh, my eyes did pop at that one, considering we've also been doing that over here since 2020 at least ;)

It really does give you the best of both worlds - resistant to typos, handling synonyms without all the usual hand-written rules, but still able to handle direct searches like ISBN…

Two big reasons for Vespa over Milvus 1.x: * Filtering * String-based IDs (a caveat that I haven't used Milvus 2.x recently, which does fix these issues, but brings in a bunch of o…

UTAH SAINTS! UTAH SAINTS! ;P (It would have been more fun if we'd spent the past month with clickbait like "What is Orgone Energy, Anyway?"

If you control the HNSW implementation, it can definitely do pre-filtering. Vespa does it, and you can modify open source HNSW libs easily. I added pre-filtering support to an inte…

It was the Gameboy version, not the C64. https://www.youtube.com/watch?v=wGIKnn-COS4

It's not a lie, yes, but it does rather undermine the entire point of the machine if you have to re-temper outside of it to use a standard shaped mold.