tuvix

I also often need EQ in the reverse situation, when I need less bass through my nice studio monitors when watching TV. Otherwise I’ll be watching Star Trek with dialogue at a normal volume and BOOM, the loudest photon torpedo you’ve ever heard.

In the context of lab hardware there’s a ton of proprietary software and barriers to automating things. I think this is less about how to communicate, and more guaranteeing that “yes, this piece of hardware can interface with an agent” and is meant to do so. Kind of like using MCP vs letting your agent make raw HTTP requests

Agreed that DuckDB as a server feels far from their initial mission, but how does async IO divert from it?

I think the fact that these kinds of companies were portrayed as such in fiction kind of prevents them from adopting the cool aesthetic. Like they need something to separate them from being the exact image of an evil futuristic corporation that lives in our heads. Or else we might actually recognize what they are.

So this is just a collection of citations to places where misaligned or illegal things happened in the real world?

Isn’t this affected heavily by adoption of a model? I feel like this might as well be a proxy for how popular a model is.

In any case it’s an interesting concept for a benchmark.

DuckDB is an in-process (now I guess less so with Quack) OLAP database for analytical workloads. PostgreSQL or MariaDB are OLTP row-oriented databases that are great for application/transaction-focused workloads but are less great when you want to query across a giant amount of data.

I don’t think I really agree with the author’s approach here, but I will say LLMs have been a huge help to me as I’ve been reviewing linear algebra and diving into signal processing. Anything in a textbook that I don’t fully grasp or am confused about, I just take a snapshot or copy paste then ask a model to derive it or explain it in different terms.

It reduces friction a ton, but at the end of the day I’m not skipping anything.

I’m not talking about the actions we take or how we might perform at certain tasks, I’m talking about how our brains actually work. My point is that we have no idea how I’m able to imagine an apple and see it in my mind’s eye. It’s basically biological magic to us at this point.

There are processes at work there that we don’t even have the language to describe.

All arguments like this boil down to semantics at a certain point, but yes large language models can “intuit” because they can generalize between examples. The issue then becomes how you pack new examples into context.

Humans can “intuit” based on a much larger, if not unlimited, context. Also I just want to say that human cognition is something so insanely complex and deep that we will not understand it at all in my lifetime. To attribute all, or really any, aspects of human cognition to a machine at this point is silly to me.

I would imagine the extension system they built would be much more difficult to manage. They could have opted for Lua, though, I suppose.

I’ve often thought of this kind of concept for a programming language.

Maybe it’s the qwerty keyboard or my bad typing habits but certain characters break my flow when typing.

Agreed, but I do think this is a wholly different kind of hype. With crypto currencies it was the promise of modernizing value exchange, with some zealots promising the end of traditional currency.

With this, I’m hearing (from supposedly reputable publications, in addition to random people) that this is going to end knowledge work in general and take out a large percentage of the world’s labor force. I’m being told to pick up a trade, and that the career I have and the knowledge I’ve gained is now worthless.

The worst part seems to be that it’s pretty much impossible to quantify any kind of impact these tools will have until after the impact is actually felt. We’ve been in limbo while the tech sector is just rotting.

I’m kind of curious why the decision to have implicit casting like this was made in the first place. I can’t think of a single upside other than not having to type out cast(foo as bar)

Not sure who you’re following on LinkedIn but this is most assuredly not the case for me or anyone I know

Extremely cool. This got me thinking that I would love to have a mermaid-like dsl for creating full tabs and apparently it exists![0]

[0] https://github.com/0xfe/vextab

Interesting! I’ll have to try a cooking the recipe for shorter. I am a bit skeptical since my family’s sauce is the best in the world already :)

Haven’t heard of forever sauce but my family makes sauce by cooking it pretty much all day. If we ate it every day then yeah we might as well keep a pot on the stove all the time

A lot of those things you mentioned have sticking power because they’re familiar to folks and migrating to something else is a big deal.

I can’t imagine most people would be able to tell the difference between Sonnet and GLM 5.2. If the infrastructure around the model you’re using doesn’t change, then swapping models is extremely easy.

I always thought that area of research had the coolest name, too: “mechanistic interpretability”

I assumed they were talking about cars and other motorists. I drive a scooter (Genuine Buddy) and have crashed before due to drivers not checking properly when at a two way stop

Interesting thought but I assume a lot of samples in the training corpus are examples of translation between languages and the same text in different languages.

Even if you could understand human cognition to the level required to say, confidently, that it’s done one word at a time, it’s likely not! Natural language is not a prerequisite for human intelligence, as evidenced by the fact that we went from primates to commenting on HN.

Natural language is, however, a prerequisite for the existence of LLMs. It’s more similar to methods for storing and retrieving information, like the printing press or a database, than it is to a sentient being.

That’s not to say that LLMs can’t do crazy things, because they already have. Our language can encode a whole lot of information, and it’s incredible that we’ve found a way to distill that so effectively.

They will absolutely be missed, maybe not by any individual but the impact of them leaving will be felt. People willing to go to bat for code quality and who are also careful about copyright and the community aspect of open source is why this whole thing worked in the first place.

I don’t play multiplayer stuff like Fortnite or Call of Duty, so I might not be your typical user. I use Steam for everything, as well.

But I fully switched to Fedora a while ago because every game I played was either just as performant or ran better on Linux. It’s plug and play, too. I just downloaded Steam and that was it.

I know there are other commenters saying the same thing, but I’m just super excited because of what this means for Linux market share on consumer machines

There’s more than two options here. It was already difficult to deal with self diagnosis for doctors, now we have a machine that outputs recommendations, and does it with confidence whether it’s correct or not.

The same issues that were present with search-engine self diagnosis are still present with LLMs. If you provide Google with an incomplete list of symptoms and can’t interpret the information you find correctly, you will likely get an incorrect diagnosis. The same is true for LLM output.

Where can you not run LuaJIT? Genuinely curious

both the Julia and Rust programming languages use curl -> sh to install

Seconding Reaper, great software. Renoise is also extremely fun to use if you’re comfortable with trackers (for midi input not that they track you) and you make electronic music

Aren’t LLMs notoriously bad at recognizing negation?

EDIT: In long context I mean

It’s possible that there’s a set of words or phrases that route deterministically to save money on obvious stuff.

I kind of wonder, though, which model they’re using to do the routing. It seems like a huge added cost to do these kinds of checks on every request