TMSJ;BI (Too Much Shitty Javascript; Barely Interacted):

Is there some kind of award for “most irredeemably ‘HN’ HN post”? Just spam a bunch of LLM comments to drive the numbers like everyone else, no need to add the whole extra step of making sure anyone trying to actually engage knows exactly how much contempt you have for their opinion.

Also, the website is so vibecoded that the logo has the wrong number of fingers. Can’t make this shit up.

It’s a screenshot of this report from a review of the UK’s security and terrorism legislation, published in December.

TechRadar article discussing the specific encryption issue here.

I was skeptical given the grammar issues others have pointed out but it seems legitimate.

Interesting, thanks for doing the research!

As an extreme non-expert, I would say “deliberate removal of a part of a model in order to study the structure of that model” is a somewhat different concept to “intrinsic and inexorable averaging of language by LLM tools as they currently exist”, but they may well involve similar mechanisms, and that may be what the OP is referencing, I don’t know enough of the technical side to say.

That paper looks pretty interesting in itself; other issues aside, LLMs are really fascinating in the way they build (statistical) representations of language.

This is a good name for one of the main reasons I’ve never really felt a desire to have an LLM rephrase/correct/review something I’ve already written. It’s the reason I’ve never used Grammarly, and turned off those infuriating “phrasing” suggestions in Microsoft Word that serve only to turn a perfectly legible sentence into the verbal equivalent of Corporate Memphis.

I’m not a writer, but lately I often deliberately edit myself less than usual, to stay as far as possible from the semantic “valley floor” along which LLM text tends to flow. It probably makes me sound a bit unhinged at times, but hey at least it’s slightly interesting to read.

I do wish the article made it clear if this is an existing term (or even phenomenon) among academics, something the author is coining as of this article, or somewhere in between.

GPT-4o mini, “Rephrase the below text in a neutral tone”:

This name is appropriate for one key reason: I have not felt the need to use an LLM for rephrasing, correcting, or reviewing my writing. This is also why I have not utilized Grammarly and have disabled the “phrasing” suggestions in Microsoft Word, which often transform a clear sentence into something overly corporate or generic.

Although I wouldn’t categorize myself as a writer, I have been intentionally editing myself less than usual lately to avoid the typical style associated with LLM-generated text. This approach might come across as unconventional at times, but it can also make for more engaging reading.

I also wish the article clarified whether this term is already established in academic circles, if the author is introducing it for the first time, or if it falls somewhere in between.

“avoid the typical style associated with LLM-generated text” – slop!

Yeah, even though I have a bit of background I can’t really make heads or tails of that OpenSearch doc at a glance, it’s dense stuff.

In my experience knowing the keywords to stick in a search engine is often half the battle; there are plenty of resources out there on “vector databases”. “Semantic search” from the lede of the OpenSearch doc might be another good one to have around.

Feel free to ask me any other questions and I can try to answer to the best of my abilities, though again, not an expert and honestly I’ve never actually used these myself beyond toy examples.

I’m not an expert, but it sounds like you want an embedding+vector database. This essentially extracts the part of an LLM that “understands” (loaded term, note the quotes) the text you put in, and then does a lookup directly on that “understanding”, so it’s very good at finding alternate phrasings or slightly differing questions.

There’s no actual text generation involved, and no need to retrain anything when adding new questions.

OpenSearch has an implementation (which I learned about just now while writing this comment and thus cannot vouch for); you could start there.

I recently started watching this, but I think I have similar feelings to you, because once it went out to the wasteland I started getting less enthused and stopped watching after a few episodes. I’ve been meaning to get back to it and see it through – although it sounds like you’re not particularly rosy on it, hearing there’s a “game show episode” makes me think I need to at least see what that’s about.

I do really like the soundtrack; New Pulse in particular has a quintessentially cyberpunk feel for me.

No mention of how it compares to existing spatial indexing methods such as R[*]-trees. That was my first thought reading the article, but they only give a comparison to naïve NxM testing. I assume this method is still an improvement in the presence of sharding, but doubt it’s the 400× quoted.