Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I made a "programming language" looking for feedback

github.com

Post reply on HN
Print view View original

21–30 of 42 posts

Re: Show HN: I made a "programming language" looking for feedback

#23

Post by Paracompact »

Chance-Device wrote: post #11

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?

Indeed, it seems to occupy a middle ground between fast-and-easy AI prompting, and slow-but-robust traditional programming. But it's still relying on AI outputs unconstrained (as far as I can tell) by more formal methods and semantic checks.

But it's also hard for me to grasp the exact value add from the README, or why I should buy their story, so I'm not sure.

Re: Show HN: I made a "programming language" looking for feedback

#24

Post by ollien »

I've been waiting for something like this to come along. I keep hearing people say LLMs are a new abstraction layer, and I fundamentally disagree. We don't commit our compiled machine code, we commit our C. Yet, with LLMs, we commit our generated source code, completely throwing away the English language abstraction.

This seems to scratch that itch. The non determinism makes it probably not suitable for most uses, though.

Re: Show HN: I made a "programming language" looking for feedback

#25

Post by nextaccountic »

mpalmer wrote: post #15
bee_rider wrote: post #12

Earlier quoted context omitted.

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.

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?

> The tech described in my comment's parent is speculative, and technically it's not even inference, once it's perfectly reproducible.

This is not true. Fabrice Bellard's ts_zip [0] and ts_sms [1] uses a LLM to compress text. It beats stuff like .xz etc but of course is much slower. Now.. if it were non-deterministic, you would have trouble decompressing exactly into what it compressed. So, it uses a deterministic LLM

[0] https://bellard.org/ts_zip/ https://news.ycombinator.com/item?id=37152978

[1] https://bellard.org/ts_sms/ https://lobste.rs/s/5srkwz/fabrice_bellard_s_ts_sms_short_me... (funny enough many people comment that, if it uses LLM, it must be lossy. This is not the case. It's compared to xz in the page because it's lossless)

Re: Show HN: I made a "programming language" looking for feedback

#26

Post by throwatdem12311 »

This is just vibe coding with extra steps.

If I have 10 bugs in production I can just regenerate my app and now I’ll have 10 completely different new bugs. New bugs on everyone’s machine! Fun for the whole family.

How does this handle multiple different “blocks” that need proper interfaces to communicate with each other.

I can only imagine the safety nightmares that would be generated in C++ this way.

Seriously…what is this for?

Re: Show HN: I made a "programming language" looking for feedback

#27

Post by zdragnar »

ollien wrote: post #24

I've been waiting for something like this to come along. I keep hearing people say LLMs are a new abstraction layer, and I fundamentally disagree. We don't commit our compiled machine code, we commit our C. Yet, with LLMs, we commit our generated source code, completely throwing away the English language abstraction. This seems to scratch that itch. The non determinism makes it probably not suitable for most uses, th…

We've had "natural language"-esque DSLs for a long time. Cucumber is probably among the better known, at least the first that comes to mind.

> Yet, with LLMs, we commit our generated source code, completely throwing away the English language abstraction.

Unless you want to commit your chats, that's very much a bonus. You don't want two different people "compiling" completely different versions of your application, because LLMs aren't deterministic.

Re: Show HN: I made a "programming language" looking for feedback

#29

Post by zahlman »

TZubiri wrote: post #19

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." Wat…

>3. The language itself misses the mark. It looks like it's C++ with some modifications?

I may have misunderstood, but my interpretation was that the "language" is really just the `$${ }$$` blocks, and the code outside of that is just written in whatever "real" (traditional?) language you want the blocks to be implemented in.

Post reply on HN