Hacker News: antononcube

New comment by antononcube in "Selkie – Opinionated TUI Framework for Raku"

antononcube — Tue, 14 Apr 2026 15:13:38 +0000

There is a set of Raku modules that leverage LLMs for different tasks (mostly code generation) using different techniques:

- https://raku.land/zef:antononcube/LLM::Resources : Uses agentic LLM-graphs with asynchronous execution

- https://raku.land/zef:antononcube/ML::FindTextualAnswer : Finds answers to questions over provided texts (e.g. natural language code generation commands)

- https://raku.land/zef:antononcube/ML::NLPTemplateEngine : Fills-in predefined code templates based on natural language code descriptions/commands

- https://raku.land/zef:antononcube/DSL::Examples : Example translations of natural language commands to executable code

New comment by antononcube in "Natural Language Processing Template Engine"

antononcube — Sat, 21 Feb 2026 21:28:22 +0000

That Python package, "NLPTemplateEngine" has Raku and Wolfram Language counterparts:

- Raku, "ML::NLPTemplateEngine"

  - https://raku.land/zef:antononcube/ML::NLPTemplateEngine

- Wolfram Language, "NLPTemplateEngine"

  - https://resources.wolframcloud.com/PacletRepository/resources/AntonAntonov/NLPTemplateEngine/

New comment by antononcube in "Day 22 – Numerically 2026 Is Unremarkable yet Happy"

antononcube — Sat, 03 Jan 2026 17:01:58 +0000

Related Number Theory notebooks / discussions:

- «Numerically 2026 is unremarkable yet happy: semiprime with primitive roots» https://community.wolfram.com/groups/-/m/t/3594686

- «Happy √2²²-22 -- And other ways to calculate 2026» https://community.wolfram.com/groups/-/m/t/3599161

Day 22 – Numerically 2026 Is Unremarkable yet Happy

antononcube — Sat, 03 Jan 2026 16:13:08 +0000

Article URL: https://raku-advent.blog/2025/12/22/day-22-numerically-2026-is-unremarkable-yet-happy/

Comments URL: https://news.ycombinator.com/item?id=46478300

Points: 5

# Comments: 2

Maze Making Using Graphs [Day 24, Raku Advent Calendar]

antononcube — Thu, 25 Dec 2025 15:28:03 +0000

Article URL: https://raku-advent.blog/2025/12/24/day-24-maze-making-using-graphs/

Comments URL: https://news.ycombinator.com/item?id=46384944

Points: 2

# Comments: 0

New comment by antononcube in "Numerically 2026 is unremarkable yet happy"

antononcube — Mon, 22 Dec 2025 14:17:40 +0000

The integer 2026 is semiprime and a happy number, with 365 as one of its primitive roots. Although 2026 may not be particularly noteworthy in number theory, this provides a great excuse to create various elaborate visualizations that reveal some interesting aspects of the number.

Numerically 2026 is unremarkable yet happy

antononcube — Mon, 22 Dec 2025 14:17:40 +0000

Article URL: https://mathematicaforprediction.wordpress.com/2025/12/21/numerically-2026-is-unremarkable-yet-happy/

Comments URL: https://news.ycombinator.com/item?id=46354288

Points: 1

# Comments: 1

Robust code generation combining grammars and LLMs

antononcube — Sat, 06 Dec 2025 18:23:40 +0000

Article URL: https://raku-advent.blog/2025/12/06/day-6-robust-code-generation-combining-grammars-and-llms/

Comments URL: https://news.ycombinator.com/item?id=46175404

Points: 3

# Comments: 1

New comment by antononcube in "Rock Paper Scissors Solitaire"

antononcube — Fri, 28 Nov 2025 19:53:31 +0000

Interesting variant. I might program it for some of the «Rock-Paper-Scissors extensions» here:

https://rakuforprediction.wordpress.com/2025/03/03/rock-pape...

Some of the extensions would need polyhedral dices:

https://demonstrations.wolfram.com/OpenDiceRolls/

New comment by antononcube in "Data science with Raku – Part 1, Data transformations and analysis"

antononcube — Fri, 28 Nov 2025 15:42:26 +0000

This document (notebook) shows transformations of a movie dataset into a format more suitable for data analysis and for making a movie recommender system. It is the first of a three-part series of notebooks that showcase Raku packages for doing Data Science (DS).

Data science with Raku – Part 1, Data transformations and analysis

antononcube — Fri, 28 Nov 2025 15:42:26 +0000

Article URL: https://rakuforprediction.wordpress.com/2025/11/27/data-science-over-small-movie-dataset-part-1/

Comments URL: https://news.ycombinator.com/item?id=46079585

Points: 7

# Comments: 2

New comment by antononcube in "Python is not a great language for data science"

antononcube — Fri, 28 Nov 2025 13:42:14 +0000

Yes, Wolfram Language (WL) -- aka Mathematica -- introduced `Tabular` in 2025. It is a new data structure with a constellation of related functions (like `ToTabular`, `PivotToColumns`, etc.) Using it is 10÷100 times faster than using WL's older `Dataset` structure. (In my experience. With both didactic and real life data of 1_000÷100_000 rows and 10÷100 columns.)

New comment by antononcube in "LLM::Functions and «the Hollywood Principle»"

antononcube — Mon, 29 Sep 2025 16:37:45 +0000

This blog post (and related notebook) show how to utilize Large Language Model (LLM) Function Calling with the Raku package "LLM::Functions".

- Package: https://raku.land/zef:antononcube/LLM::Functions

- Notebook: https://github.com/antononcube/RakuForPrediction-blog/blob/m...

LLM::Functions and «the Hollywood Principle»

antononcube — Mon, 29 Sep 2025 16:37:45 +0000

Article URL: https://rakuforprediction.wordpress.com/2025/09/28/llm-function-calling-workflows-part-4-universal-specs/

Comments URL: https://news.ycombinator.com/item?id=45415790

Points: 4

# Comments: 1

New comment by antononcube in "Asynchronous LLM computations specifications with LLM:Graph"

antononcube — Sun, 28 Sep 2025 21:07:30 +0000

Mostly, because Python is not a good a "discovery" and prototyping language. It is like that by design -- Guido Van Rossum decided that TMTOWTDI is counter-productive.

Another point, which could have mentioned in my previous response -- Raku has more elegant and easy to use asynchronous computations framework.

IMO, Python's introspection matches that Raku's introspection.

Some argue that Python's LLM packages are more and better than Raku's. I agree on the "more" part. I am not sure about the "better" part:

- Generally speaking, different people prefer decomposing computations in a different way. - When few years ago I re-implemented Raku's LLM packages in Python, Python did not have equally convenient packages.

New comment by antononcube in "Asynchronous LLM computations specifications with LLM:Graph"

antononcube — Sun, 28 Sep 2025 16:04:00 +0000

Ah, yes, Raku's "LLM::Graph" is heavily inspired by the design of the function LLMGraph of Wolfram Language (aka Mathematica.)

WL's LLMGraph is more developed and productized, but Raku's "LLM::Graph" is catching up.

I would like to say that "LLM::Graph" was relatively easy to program because of Raku's introspection, wrappers, asynchronous features, and pre-existing LLM functionalities packages. As a consequence the code of "LLM::Graph" is short.

Wolfram Language does not have that level introspection, but otherwise is likely a better choice mostly for its far greater scope of functionalities. (Mathematics, graphics, computable data, etc.)

In principle a corresponding Python "LLMGraph" package can be developed, for comparison purposes. Then the "better choice" question can be answered in a more informed manner. (The Raku packages "LLM::Functions" and "LLM::Prompts" have their corresponding Python packages implemented already.)

New comment by antononcube in "Asynchronous LLM computations specifications with LLM:Graph"

antononcube — Sun, 28 Sep 2025 15:29:52 +0000

Specifications for asynchronous LLM computations with Raku's "LLM::Graph" detail how to manage complex, multi-step LLM workflows by representing them as graphs. By defining the workflow as a graph, developers can execute LLM function calls concurrently, enabling higher throughput and lower latency than synchronous, step-by-step processes.

"LLM::Graph" uses a graph structure to manage dependencies between tasks, where each node represents a computation and edges dictate the flow. Asynchronous behavior is a default feature, with specific options available for control.

Asynchronous LLM computations specifications with LLM:Graph

antononcube — Sun, 28 Sep 2025 15:29:52 +0000

Article URL: https://rakuforprediction.wordpress.com/2025/08/23/llmgraph/

Comments URL: https://news.ycombinator.com/item?id=45405068

Points: 5

# Comments: 8

New comment by antononcube in "TallMountain – Stoic Virtue Ethics for an LLM Agent"

antononcube — Fri, 26 Sep 2025 01:00:57 +0000

God to know.

BTW, several years ago the LLM-revolution didn't happen yet. Raku started to have sound LLM packages circa March-May 2023.

New comment by antononcube in "TallMountain – Stoic Virtue Ethics for an LLM Agent"

antononcube — Thu, 25 Sep 2025 22:01:37 +0000

What is better in Raku than Python? Did you use any of the dedicated Raku LLM packages?