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

Nanolang: A tiny experimental language designed to be targeted by coding LLMs

github.com

Post reply on HN
Print view View original

191–200 of 210 posts

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#191

Post by jkh99 »

wiremine wrote: post #170

I like the creativity, but I'm not sure it's needed. I've been building a large-scale database system using Opus 4.5, and targeting Rust. It's not perfect, but the Rust compiler is so helpful that Opus has solved a lot of problems on its own. I have around 100,000 lines of code, and have completed some major refactoring. I am using a variation of spec-driven development.

This absolutely was NOT needed, just to be clear, it was just fun to do and, perhaps more importantly, it taught me a lot in the process of making it.

I also have a few geometric 3D printed objects on my desk that I made with openscad as "printing challenges" and then beat my head against my 3D printers for hours trying to actually print them. They did not need to be printed, they serve no purpose other than to be aesthetically pleasing and educational. :)

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#192

Post by UltraSane »

deepsquirrelnet wrote: post #25

At this point, I am starting to feel like we don’t need new languages, but new ways to create specifications. I have a hypothesis that an LLM can act as a pseudocode to code translator, where the pseudocode can tolerate a mixture of code-like and natural language specification. The benefit being that it formalizes the human as the specifier (which must be done anyway) and the llm as the code writer. This also might e…

Opus 4.5 is very good at using TLA+ specifications to generate code.

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#193

Post by nl »

measurablefunc wrote: post #186
nl wrote: post #182

Earlier quoted context omitted.

Sure. The point is that your statement about the ability to do RL is wrong. Additionally your response to the Deepseek paper in the other subthread shows profound and deliberate ignorance.

Theorycrafting is very easy. Not a single person in this thread has shown any code to do what they're suggesting. You have access to the best models & yet you still haven't managed to prompt it to give you the code to prove your point so spare me any further theoretical responses. Either show the code to do exactly what you're saying is possible or admit you lack the relevant understanding to back up your claims.

> You have access to the best models & yet you still haven't managed to prompt it to give you the code to prove your point so spare me any further theoretical responses. Either show the code to do exactly what you're saying is possible

GPU poor here though...

To quote someone (you...) on the internet:

> More generally, don't ask random people on the internet to do work for you for free.

https://news.ycombinator.com/item?id=46689232

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#194

Post by nl »

nxobject wrote: post #187
nl wrote: post #72

Earlier quoted context omitted.

I have a vibe coded fantasy console. Getting Doom running on it was easy. Getting the Doom sound working on it involved me setting there typing "No I can't hear anything" over and over until it magically worked... Maybe I should have written a helper program to listen using the microphone or something.

I was reading an Ars article by someone who'd hacked up Apple II and Atari 2600 emulators to provide state introspection/reproducible input via MCP, sockets, file I/O - would that work? https://github.com/benj-edwards/atari800-ai https://github.com/benj-edwards/bobbin

wow I love it.

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#195

Post by nl »

measurablefunc wrote: post #177
whimsicalism wrote: post #153

Earlier quoted context omitted.

well, that’s one way to react to being provided with interesting reading material.

Bring up passage that supports your claim. I'll wait.

Not exactly sure what you are looking for here.

That GRPO works?

> Group Relative Policy Optimization (GRPO), a variant reinforcement learning (RL) algorithm of Proximal Policy Optimization (PPO) (Schulman et al., 2017). GRPO foregoes the critic model, instead estimating the baseline from group scores, significantly reducing training resources. By solely using a subset of English instruction tuning data, GRPO obtains a substantial improvement over the strong DeepSeekMath-Instruct, including both in-domain (GSM8K: 82.9% → 88.2%, MATH: 46.8% → 51.7%) and out-of-domain mathematical tasks (e.g., CMATH: 84.6% → 88.8%) during the reinforcement learning phase

Page 2 of https://arxiv.org/pdf/2402.03300

That GRPO on code works?

> Similarly, for code competition prompts, a compiler can be utilized to evaluate the model’s responses against a suite of predefined test cases, thereby generating objective feedback on correctness

Page 4 of https://arxiv.org/pdf/2501.12948

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#196

Post by measurablefunc »

nl wrote: post #193
measurablefunc wrote: post #186

Earlier quoted context omitted.

Theorycrafting is very easy. Not a single person in this thread has shown any code to do what they're suggesting. You have access to the best models & yet you still haven't managed to prompt it to give you the code to prove your point so spare me any further theoretical responses. Either show the code to do exactly what you're saying is possible or admit you lack the relevant understanding to back up your claims.

> You have access to the best models & yet you still haven't managed to prompt it to give you the code to prove your point so spare me any further theoretical responses. Either show the code to do exactly what you're saying is possible GPU poor here though... To quote someone (you...) on the internet: > More generally, don't ask random people on the internet to do work for you for free. https://news.ycombinator.com/i…

Claims require evidence & if you are unwilling to present it then admit you do not have any evidence to support your claims. It's not complicated. Either RL works & you have evidence or you do not know & can not claim that it works w/o first doing the required due diligence which (shockingly) actually requires work instead of empty theory crafting & hand waving.

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#197

Post by measurablefunc »

nl wrote: post #195
measurablefunc wrote: post #177

Earlier quoted context omitted.

Bring up passage that supports your claim. I'll wait.

Not exactly sure what you are looking for here. That GRPO works? > Group Relative Policy Optimization (GRPO), a variant reinforcement learning (RL) algorithm of Proximal Policy Optimization (PPO) (Schulman et al., 2017). GRPO foregoes the critic model, instead estimating the baseline from group scores, significantly reducing training resources. By solely using a subset of English instruction tuning data, GRPO obtains…

None of those are novel domains w/ their own novel syntax & semantic validators, not to mention the dearth of readily available sources of examples for sampling the baselines. So again, where does it say it works for a programming language with nothing but a grammar & a compiler?

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#198

Post by verdverm »

catlifeonmars wrote: post #190
verdverm wrote: post #160

Earlier quoted context omitted.

it's more a mathematical / algorithmic limitation

I’ll counter it’s an architectural issue

I would put that under the umbrella of algo/math, i.e. the structure of the LLM is part of the algo, which is itself governed by math

For example, DeepSeek has done some interesting things with attention, via changes to the structures / algos, but all this is still optimized by gradient descent, which is why models do not learn facts and such from a single pass. It takes many to refine the weights that go into the math formulas

Re: Nanolang: A tiny experimental language designed to be targeted by coding LLMs

#200

Post by catlifeonmars »

verdverm wrote: post #198
catlifeonmars wrote: post #190

Earlier quoted context omitted.

I’ll counter it’s an architectural issue

I would put that under the umbrella of algo/math, i.e. the structure of the LLM is part of the algo, which is itself governed by math For example, DeepSeek has done some interesting things with attention, via changes to the structures / algos, but all this is still optimized by gradient descent, which is why models do not learn facts and such from a single pass. It takes many to refine the weights that go into the ma…

> I would put that under the umbrella of algo/math, i.e. the structure of the LLM is part of the algo, which is itself governed by math

Yes you’re right. I misspoke.

I’m curious if there are ways to get around the monolithic nature of today’s models. There have to be architectures where a generalized model can coordinate specialized models which are cheaper to train, for example. E.g calling into a tool which is actually another model. Pre-LLM this was called boosting or “ensemble of experts” (I’m sure I’m butchering some nuance there).

Post reply on HN