[HN Gopher] Show HN: I made a "programming language" looking for...
       ___________________________________________________________________
        
       Show HN: I made a "programming language" looking for feedback
        
       Author : alonsovm
       Score  : 21 points
       Date   : 2026-03-29 18:35 UTC (4 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | zahlman wrote:
       | So instead of auto-completing bits of LLM-generated code into the
       | codebase, you preprocess it in. I can imagine a lot of devs won't
       | like the ergonomics of that, but I like the idea that you can
       | keep both original .glp and generated source files in version
       | control.
       | 
       | I'd strongly recommend going over the README by hand. What you
       | currently have is redundant and disorganized, and header
       | sizes/depths don't make a lot of sense. The "manual build"
       | instructions should also describe the dependencies that the
       | install script is setting up.
        
       | bojanstef4 wrote:
       | did you know "glup" (pronounced gloop) in serbian means "stupid"
        
         | burgerone wrote:
         | Glup is indeed not the name of the project.
        
       | mpalmer wrote:
       | The language feels like a solution in search of a problem, and
       | the mostly-generated README reduces my confidence in the quality
       | of the project before I've even learned that much about it.
       | 
       | One example:                   Best of all, they work together.
       | You can store your .glp blueprints in a Docker container--
       | creating software that is immortal in both environment and logic.
       | 
       | This is nonsensical. The entire point of a container is it ought
       | to contain only what's necessary to run the underlying software.
       | It's just the production filesystem. Why would I put LLM prompts
       | that don't get used at runtime in a container?
       | 
       | What other language-agnostic methods of describing complex
       | systems is your project inspired by? In competition with?
       | 
       | ---
       | 
       | By using this tool, a programmer or team is sending the message
       | that:
       | 
       | "We expect LLM generated code to remain a deeply coupled part of
       | our delivery process, indefinitely"
       | 
       | But we didn't know about LLMs 5 years ago. What is the argument
       | for defining your software in a way that depends on such a young
       | technology? Most of the "safety" features here are related to how
       | _unsafe_ the tech itself still is.
       | 
       | "Nontrivial LLM driven rewrites of the code are expected, even
       | encouraged"
       | 
       | Why is the speedy rewriting of a system in a new language such a
       | popular flex these days? Is it because it looks impressive, and
       | LLMs make it easy? It's so silly.
       | 
       | And if the language allows for limiting the code the LLM is
       | allowed to modify, how is it going to help us keep our overall
       | project language-agnostic?
        
       | bdcravens wrote:
       | I've found that writing pseudocode in a markdown file with little
       | to no definitions (I may put a few non-obvious notes in the
       | CLAUDE/AGENTS files) and telling the agent what language to turn
       | it into generally works.
        
       | Retr0id wrote:
       | I've been thinking about something along these lines, but coupled
       | with deterministic inference. At each "macro" invocation you'd
       | also include hash-of-model, and hash-of-generated-text. (Note,
       | determinism doesn't require temperature 0, so long as you can
       | control the rng seed. But there are a lot of other things that
       | make determinism hard)
       | 
       | You could take it a step further and have a deterministic agent
       | inside a deterministic VM, and you can share a whole project as
       | {model hash, vm image hash, prompt, source tree hash} and have
       | someone else deterministically reproduce it.
       | 
       | Is this useful? Not sure. One use case I had in mind as a
       | mechanism for distributing "forbidden software". You can't
       | distribute software that violates DMCA, for example, but can you
       | distribute a prompt?
        
         | mpalmer wrote:
         | Deterministic inference is mechanically indistinguishable from
         | decompression or decryption, so if there's a way to one-weird-
         | trick DMCA, it's probably not this.
        
           | bee_rider wrote:
           | You'd think that, but it sees like big business and
           | governments are treating inference as somehow special. I
           | dunno, maybe low temperatures can highlight this weird
           | situation?
           | 
           | Temperature is an easy knob to twist, after all. Somebody
           | (not me I'm too poor to pay the lawyers) should do a search
           | and find where the crime starts.
        
             | Retr0id wrote:
             | What does temperature have to do with anything?
        
               | bee_rider wrote:
               | Or however deterministic inference is supposed to happen.
               | I don't know LLMs.
        
             | mpalmer wrote:
             | Well, it's still not deterministic even at temp 0. The tech
             | described in my comment's parent is speculative, and
             | technically it's not even inference, once it's perfectly
             | reproducible.
             | 
             | At that point it's retrieving results from a database.
             | 
             | EDIT: how would OP address my main point, which is that
             | det. inference is functionally equivalent to any arbitrary
             | keyed data storage/retrieval system?
        
               | Retr0id wrote:
               | Deterministic inference isn't speculative, it's
               | achievable if you want it. It's just not the default.
        
       | whoamii wrote:
       | Why didn't you implement this in... Glupe?
        
       | kgeist wrote:
       | Glupe means "stupid" in Slavic languages, was it on purpose?
        
         | LatencyKills wrote:
         | From their agent-rules.md:
         | 
         | > This is not negotiable. This is not optional. You cannot
         | rationalize your way out of this.
         | 
         | Some days I really miss the predictability of a good old
         | if/else block. /s
        
       | Chance-Device wrote:
       | But... why not just write pseudo code, or any language you
       | actually know, and just ask the AI to port it to the language you
       | want? That's a serious question by the way, is there some use
       | case here I'm not seeing where learning this new syntax and
       | running this actually helps instead of being extra steps nobody
       | needs?
        
       | JoeAltmaier wrote:
       | I wrote a programming language, some time back. You need a good
       | reason to add to the tumult in the marketplace, and I thought I
       | had one. My language was for discrete control systems. You could
       | declare samplers for data values (interval, sensor, type) and
       | name them as variables. You could create control actions by
       | listing a set of one or more sampler variables in brackets. Once
       | there were 'fresh' values for all of the samplers, the action
       | would be invoked.
       | 
       | It had the usual functions and i/o library stuff. In fact I wrote
       | a tool to absorb other library headers e.g. C or C++ and product
       | blocks that my compiler could link with, and voila your program
       | could call those external libraries.
       | 
       | We used it for a couple of contracts. Some of the control
       | engineers were enthusiastic; some not so much. One more thing to
       | learn.
        
       | TZubiri wrote:
       | Some feedback, in order from most to least important:
       | 
       | > 1- installing with irm
       | https://raw.githubusercontent.com/alonsovm44/glupe/master/in... |
       | iex
       | 
       | That is high risk, don't ask people to do that, especially when
       | it's completely unnecessary for what the language is, and the
       | language isn't providing value, it's just esoterical.
       | 
       | >2. "Glupe isolates AI logic into semantic containers, so your
       | manual code stays safe."
       | 
       | Watchout for light-AI psychosis. This existed before AI to be
       | fair, but using words in a way that doesn't convey meaning. Maybe
       | what's going on is that you use them with ChatGPT and it either
       | understands or doesn't but follow along. So make sure to
       | prioritize language that you develop with humans, not AI. And try
       | to simplify your language and the message you were trying to
       | convey, because you missed bigtime with that sentence.
       | 
       | >3. The language itself misses the mark. It looks like it's C++
       | with some modifications?
       | 
       | 4- it's also not a language but a terminal? Try to get the trust
       | of your users by doing one thing well before promising to do it
       | all. A bit of humility pays off, you can't do everything anyways.
        
       | empressplay wrote:
       | I agree that some form of shorthand between pseudocode and actual
       | code would be really useful to improve accuracy on LLM requests
       | but I don't think this is quite it. Ideally it would be as simple
       | as possible, but not rely on language-specific paradigms. Sort of
       | a pidgin that everyone would understand, that used white space
       | and indentation to indicate things like loops and such. Something
       | a normal person could look at and still largely comprehend.
        
       ___________________________________________________________________
       (page generated 2026-03-29 23:00 UTC)