Can you imagine an (Android) app store model? You know when you buy packaging that it's verified. Complies with regulations. Companies submit packaging for review that's cheap, fast, tax-supported, and EU-wide. Doesn't have to be like the FDA. So that reusables could become a thing, I'd be fine honestly with extra charges for most branded packaging. This butts up against freedom of expression I suppose but come on the single-use plastics problem is real. But as described what sounds exactly backwards is the EU model.
Radiohead sang, "If I were king you'd be backed up against the wall" but I'd sing, "Send your goods in any verified packaging!"
Oh I agree the LLM not reasoning at the AST level, and was trying to say I believed this even more strongly than the person I was replying to, but that it didn't matter if you coded or had the LLM code in an appropriate style for a lisp. And then I made a tried to hint at a further claim that the base LLM is not reasoning at all beyond its attention heads I think. As I understand it the corpus space itself -- meaning the relations between tokens and lexemes and so on -- contains the shape of what we call reasoning, so that the language itself + weighting , attention heads, is doing any "reasoning" at all unless the LLM directly starts a chain-of-reasoning where it talks to itself, and if it's doing that just for one's delimiters then one probably hasn't used the lisp very well. I was probably unclear and sounding like I thought the LLM was fundamentally a reasoning device. As far as I understand, "reasoning" or an internal model other than the the language (training corpus corpus) + weights only exists when an LLM does "self talk" either as sub turns, a strong but expensive hack, or as a result of multiple turns layering up context. My claim is that the model can get delimiters right despite not reasoning about them, but deeply nested. My sense is that the model doesn't need to reason to track until attention heads are overwhelmed by nested delimiters; does those sound right? Anyway super interesting conversation, and I do think I was giving less credit to LLM reasoning, as seems to me an LLM trained on AST might still get it wrong a lot. So I don't tend to think AST is something that in and of itself makes languages with ASTs any better. But... immutability, which is practical thanks to AST, is another story. And if I'm wrong about anything here please let me know; I'm not an expert!
Paren issues with Clojure probably mean your functions are too long? I like to keep mine down to 8-10 lines or less when possible, keep them flat and composable, use threading macro and then transducers for performance. At least that's how I read it. AST might not matter much either way, or in a stranger way, because the LLM's corpus and progression through code will give it a kind of shadow or grooves of an ast, but it isn't making or receiving any ast from this piece of code.
Still, Elixir scores best on the TenCent AutoCodebench, by far actually, "despite" being like Clojure built with an AST and immutability. Clojure wasn't part of those tests but I use both daily with LLMs (mostly Codex) and imagine it's on par with Elixir. The repl is better than Elixir's. Both have serious strengths.
Yeah great point. In my case I'd dropped Clojure and then returned because of how I could use it with LLMs. Still, the good news is maybe that LLMs don't just kill everything but three languages.
Hehe, a good joke, but to be a little boring, Clojure is successful and excellent and LLMs love it in my experience. And it's better in LLM era because there little frictions get agented away so to speak but the benefits mostly remain and are even amplified, like immutability as an example. Parens with overlong functions can be an issue but it's really not such a horror show. And Datomic-flavored Datalog in a Clojure triplestore feels almost made to order for LLMs.
If machines start doing all of the work, even much or most cognitive work, then I think this has to change. Meanwhile look at Nordic countries for example. Not communist, rich, low inequality by design. They were the pioneers btw in social democracy, in which they all live. Interesting, "always been history" is actually not right, or at least, also, it's "not been pre-history" is right because early humans before and up to us as homo sapiens, did indeed from all evidence I've seen have dramatically greater social equality and sharing economies. Our current state is the less "natural" in the sense of being out of tune with our instincts.
We have state supported pension plans in most developed countries, unemplyment insurance, these large welfare states with extensive public education, national health and so on, so while the means of production mostly haven't been socialized, the fruits often have, through taxation. Now, some of this existed before the Industrial Revolution -- I wasn't aware how much until I read Karl Polanyi's The Great Transformation, which is a more important book now than ever, I humbly propose, but the scale is dwarfed by what we have now. And as Polanyi points out, we did get socialism as a response, as well as fascism, which was often btw called corporatism (as in the nation as a single body, not having to do with companies). Liberal democratic capitalism won out, for a while, and in large part because it became social democracy, or so goes a claim to which I subscribe. Without the social welfare aspects of modern democracy, the system would likely have broken politically.
I must say this truly depends. I can sometimes be more focused with an audiobook. An extreme example? Heidegger's Being and Time, Macquarie and Robinson translation. The audiobook version read by Martyn Swain is a godsend for helping one try to grapple with this monster. Though his only commentary is in timbre, rhythm, speed, it absolutely enriches the reading. The audiobook is something like 24 hours long, but there's just no way you finish in that time (if you ever do finish); if you're like me you've gotta rewind rewind rewind, baby.
A talented reader can work magic. Ukemi and Naxos have great titles.
Of course it's possible, but reading and watching fiction feel very different and can you see a way to change that? The word may continue to decline compared to image. But the image is soon to become nearly as cheap and hackable as the word.
To me this is almost like a tone-deaf naming change.
Empty Slot (new Pro as Mythos competitor?)
Old Pro -> now Flash
Old Flash -> now Flash Lite
Old Flash Lite -> now Gemma (and not served by Google)
I say "almost" because the situation is more fluid and unstable than a normal naming change. If Apple were to do this with laptops, maybe it'd be like, Air gets better and pricier and becomes Pro-level model, Neo same way becomes Air-level model, etc. But Apple's too design oriented to do something like that. Google, well...
This change has made me decide to move to a multi-provider situation like through OpenRouter for consumer-facing LLM api in a service I'm building. I just can't trust Google to not constantly rearrange everything under our feet. Doesn't mean I won't use Gemini, but it clearly means I need to have others in the mix ready to go. In fact I used to use lots of Flash Lite, which is now Gemma territory, and I can't get that served by Google anymore and don't want to run my own hardware.
But in any case, I'd compare this "Flash" model with previous "Pro" on all metrics. It's kinda like if in clothes a Small suddenly became what was a Large, or at Starbucks a Grande became the new de facto Venti. And only for the new! drinks.
And if we think this way, it's possible that prices are actually falling?
Well in a recent project I tried TypeScript thinking, OK, LLMs, huge training corpus! massive adoption! api for everything already set up! swim with the current! and I tried various frameworks and so on, but for me reasoning about things and being able to make systems that I could adapt and pivot it was honestly inferior compared to niche Elixir and Clojure. But it's not like I hate JS; I use it in LiveView all the time. And don't mean to imply there are no problems in niche-land though; you've got to be willing to do more yourself and live in a tiny world. Really, LLMs kind of tamed Clojure for me because it seems so far at least that they can handle the glue code and stitching libraries together pretty decently as long as you don't get lazy with architectural choices and stay vigilant. And if I ever hire it pretty much has to be remote or learn on the job, though again LLMs reduce this pain greatly.
For me, I need to move fast and already knew Phoenix well, LiveView fits my use case, and websockets setup with Phoenix is very clear so switching to a two-language setup seemed better than CLJS. I could have gone CLJS re-frame and all that but it would have been more work and more unknowns. I call LLMs from Elixir also so all of the reconnect, backoffs, papercuts, shenanigans and so on, well I just know how to do this kind of thing better in Elixir. In its way Elixir is a great, like, defensive language. I was able to keep most async in Elixir and Clojure mostly synchronous. There was some pain though with bridge between the two and at times I thought I'd made a mistake. Clojure is fantastic with data and Datalog databases, so no regret. Outside world deals with Elixir, and the temple is in Clojure and Datalog.
Using Clojure and Elixir and LLMs are fantastic with both. Sure, if I get to a super-stable situation then maybe I'd consider moving to Rust (or Jank?), but for now I'm just so happy with Clojure and Elixir in this new world. I'm solving new problems with fully bespoke architecture so the flexibility is key. Clojure for business logic and most DB. With Elixir, it's the actor model and hand-holding as I'm using it for the web layer. I bet Ruby on Rails would also shine for some cases, prob most CRUD for example.
I'd be interested in soft drinks that were unsweetened altogether and not just sugar free. Sometimes I have sparkling water + apple cider vinegar + lemon/lime juice and it's wonderful when well mixed.
VS Code and its forks (Cursor, Antigravity, etc.) have Calva, a fantastic REPL with excellent linter Kondo. These are amazing tools; formatting is the very least of it. You don't need Emacs. I personally using VS Code + Doom Emacs. Also, many packages that look abandoned are simply mature. You can literally use ten year old packages.
I'm not a hot shot programmer, entirely self-taught but a decent architect who thinks hard about problems, and with LLM agents Clojure shines for me. There are some fantastic databases also starting with Datomic -- free now thanks to Nubank -- and everything inspired by it and the Clojure flavor of Datalog. These include Datalevin, Datahike, DataScript, XTDB. Datomic itself is probably best for enterprise though there's now an embedded version.
But I'm pretty convinced that most LLMs I've used are more reliable with Clojure (and Elixir) than with most of the popular languages, and I can say they use Datalog extremely well, seemingly much better than SQL despite the vast difference in corpus size. For one thing Datalog just gets rid of joins issues.
Btw Datomic is free now that Nubank supports it (and runs a large bank on it).
There's also a fantastic kind of mini, FOSS, file-based Datomic-style Datalog DB that's not immutable called Datalevin. Uses the hyper-fast LMDB under the hood. It's called Datalevin. https://github.com/juji-io/datalevin
I agree with all of these except the emotional impact of war where though slower a novel or memoir might work best. Think "All Quiet on the Western Front." At the same time we do want images of the war and time for grounding.