Hacker News: lafalce

New comment by lafalce in "Someone Build a OS for Claude Code"

lafalce — Tue, 23 Jun 2026 00:22:59 +0000

Basically — to get AI-generated Hacker News comments with em dashes :)

Someone Build a OS for Claude Code

lafalce — Sun, 21 Jun 2026 18:58:37 +0000

Article URL: https://github.com/mateolafalce/claudios/blob/main/README.md

Comments URL: https://news.ycombinator.com/item?id=48621576

Points: 2

# Comments: 2

Benchmark Comparison: JSONL vs. TOON output for JSON-render efficiency

lafalce — Wed, 21 Jan 2026 15:17:12 +0000

Article URL: https://github.com/vercel-labs/json-render/issues/33

Comments URL: https://news.ycombinator.com/item?id=46706853

Points: 2

# Comments: 0

I Cut Vercel's JSON-Render LLM Costs by 89% Using Toon

lafalce — Sat, 17 Jan 2026 14:17:22 +0000

Article URL: https://mateolafalce.github.io/2026/I%20Cut%20Vercel%27s%20json-render%20LLM%20Costs%20by%2089%25%20Using%20TOON/ICutVercelsjsonrenderLLMCostsby89UsingTOON.html

Comments URL: https://news.ycombinator.com/item?id=46658248

Points: 1

# Comments: 0

Show HN: Recursive Language Model for Querying Human Action by Ludwig von Mises

lafalce — Fri, 16 Jan 2026 11:56:23 +0000

Human Action by Ludwig von Mises is a 900+ page treatise on economics and praxeology dense, complex, and foundational to Austrian economics.

I built this tool using Recursive Language Models (RLM) that ingests the entire book and lets you query it conversationally. It downloads the full text from mises.org, processes it with RLM for deep contextual understanding, and serves a simple Flask frontend. Perfect for students, researchers, or anyone curious about Mises's ideas!

Comments URL: https://news.ycombinator.com/item?id=46645564

Points: 2

# Comments: 0

Topic2Manim Now Has a UI

lafalce — Tue, 13 Jan 2026 19:09:27 +0000

Article URL: https://github.com/mateolafalce/topic2manim

Comments URL: https://news.ycombinator.com/item?id=46606155

Points: 1

# Comments: 0

Show HN: Turn any topic into a 3Blue1Brown-style video

lafalce — Sat, 10 Jan 2026 01:35:53 +0000

Hey HN! I built Topic2Manim to automate the creation of educational videos like those from 3Blue1Brown.

The workflow is simple:

1. Give it any topic (e.g., "how ChatGPT works")

2. An LLM generates an educational script divided into scenes

3. LLM generates Manim code for each scene

4. FFmpeg concatenates everything into a final video

Currently working on TTS integration for narration!

Would love feedback on the approach and ideas for the TTS integration

Comments URL: https://news.ycombinator.com/item?id=46561801

Points: 5

# Comments: 0

The Engine of Computer Vision

lafalce — Wed, 07 Jan 2026 18:57:44 +0000

Article URL: https://mateolafalce.github.io/2026/The%20Engine%20of%20Computer%20Vision/TheEngineofComputerVision.html

Comments URL: https://news.ycombinator.com/item?id=46530841

Points: 1

# Comments: 0

Stop Using Softmax for Everything

lafalce — Sat, 03 Jan 2026 22:25:09 +0000

Article URL: https://mateolafalce.github.io/2026/The%20One%20Cake%20Fallacy%20%28Softmax%20vs.%20Sigmoid%29/TheOneCakeFallacy_Softmaxvs.Sigmoid_.html

Comments URL: https://news.ycombinator.com/item?id=46482357

Points: 4

# Comments: 1

Logistic Regression, the Sigmoid, and Log Loss

lafalce — Sat, 03 Jan 2026 02:26:14 +0000

Article URL: https://mateolafalce.github.io/2026/Logistic%20Regression%2C%20the%20Sigmoid%2C%20and%20Log%20Loss/LogisticRegressiontheSigmoidandLogLoss.html

Comments URL: https://news.ycombinator.com/item?id=46472162

Points: 2

# Comments: 0

Decision Trees vs. Boosting: The One Expert vs. the Committee

lafalce — Thu, 01 Jan 2026 17:12:54 +0000

Article URL: https://mateolafalce.github.io/2026/Decision%20Trees%20vs.%20Boosting_%20The%20One%20Expert%20vs.%20The%20Committee/DecisionTreesvs.BoostingTheOneExpertvs.TheCom.html

Comments URL: https://news.ycombinator.com/item?id=46455819

Points: 1

# Comments: 0

Understanding Decision Trees: The White Box of Machine Learning

lafalce — Wed, 31 Dec 2025 20:29:27 +0000

Article URL: https://mateolafalce.github.io/2025/Understanding%20Decision%20Trees_%20The%20White%20Box%20of%20Machine%20Learning/UnderstandingDecisionTreesTheWhiteBoxofMachin.html

Comments URL: https://news.ycombinator.com/item?id=46447955

Points: 2

# Comments: 0

The Comprehensive Cognition Blog

lafalce — Mon, 22 Dec 2025 21:15:33 +0000

Article URL: https://mateolafalce.github.io/

Comments URL: https://news.ycombinator.com/item?id=46359186

Points: 3

# Comments: 0

I Cloned Myself with a Markov Chain

lafalce — Fri, 19 Dec 2025 18:03:53 +0000

Article URL: https://mateolafalce.github.io/2025/I%20Cloned%20Myself%20with%20a%20Markov%20Chain/IClonedMyselfwithaMarkovChain.html

Comments URL: https://news.ycombinator.com/item?id=46328862

Points: 2

# Comments: 0

New comment by lafalce in "The Future of the Linux-rs Project"

lafalce — Sun, 14 Dec 2025 21:57:26 +0000

After two years working on the linux-rs project, I've decided to pause development. I'm certain that not even thousands of developers could rewrite the Linux kernel from C to Rust within a decade.

With the LLM revolution, I believe the real challenge isn't manually rewriting the kernel, but researching and pursuing a recursive alternative through RL-based models.

The Future of the Linux-rs Project

lafalce — Sun, 14 Dec 2025 21:57:26 +0000

Article URL: https://mateolafalce.github.io/2025/The%20Future%20of%20the%20Linux-rs%20Project/TheFutureoftheLinuxrsProject.html

Comments URL: https://news.ycombinator.com/item?id=46267439

Points: 2

# Comments: 1

Integrating Toon into Visual Studio Code

lafalce — Thu, 11 Dec 2025 14:17:52 +0000

Article URL: https://github.com/mateolafalce/toon-context-optimizer

Comments URL: https://news.ycombinator.com/item?id=46231664

Points: 1

# Comments: 0

New comment by lafalce in "I'm Peter Roberts, immigration attorney who does work for YC and startups. AMA"

lafalce — Fri, 05 Dec 2025 19:21:44 +0000

Hi Peter, thanks for your time :)

I am planning to move to San Francisco to join the startup ecosystem. Regarding the H-1B visa, what does the current process and timeline look like for a new applicant? Given the lottery constraints, are there specific 'red flags' or common mistakes I should avoid when looking for a sponsor?

New comment by lafalce in "My Contribution to Toon"

lafalce — Tue, 02 Dec 2025 14:45:50 +0000

As I mentioned on my X account, from my point of view, the TOON format shouldn't be utilized just like JSON (constructing data structures in .toon format to send to the LLM).

I believe TOON is a real game changer when used as an intermediary between the IDE/chat and the LLM. That hasn't been implemented yet, but it is undoubtedly the next step toward the project's mass adoption.

There will surely be news regarding this in the coming weeks :)

My Contribution to Toon

lafalce — Tue, 02 Dec 2025 14:45:50 +0000

Article URL: https://mateolafalce.github.io/2025/My%20Contribution%20to%20TOON/MyContributiontoTOON.html

Comments URL: https://news.ycombinator.com/item?id=46121708

Points: 2

# Comments: 1