Hacker News: vfalbor

Ecotypes Harbor the Genetic Memory of a Species' Past

vfalbor — Mon, 08 Jun 2026 07:24:24 +0000

Article URL: https://www.quantamagazine.org/how-ecotypes-harbor-the-genetic-memory-of-a-species-past-20260521/

Comments URL: https://news.ycombinator.com/item?id=48442264

Points: 5

# Comments: 0

New comment by vfalbor in "Michael Burry says neither SpaceX nor Anthropic is worth $1T"

vfalbor — Mon, 08 Jun 2026 07:21:35 +0000

If that were the case, it would be reasonable to expect that companies like OpenAI or Anthropic, which are heavily indebted, would lose part of their business model, not because their models are bad, but because others will be cheaper and not as bad.

New comment by vfalbor in "Michael Burry says neither SpaceX nor Anthropic is worth $1T"

vfalbor — Tue, 02 Jun 2026 12:48:18 +0000

This is a very interesting comment. Companies like OpenAI or ChatGPT sell hardware hidden in tokens, and the token is different for each company depending on the tokenizer. The concern is this: when you have an Opus 4.7, Sonnet, or GPT 5X with an Nvidia H100 or H200 GPU, what will happen to this cost when, if not Nvidia, another Chinese company enters the market and starts running these models? The point here is that as long as Nvidia is the provider, and limits access to the machines and the number of data centers is also limited, these companies can be worth whatever they want. But the moment this starts to expand, the value will surely decline, because what you're selling isn't the model itself, which is ultimately just a 1 TB file that you have replicated across machines. What you're selling is access to a software program on a specialized machine. As long as you control the resource, which in this case is that machine, you'll have value. The moment other machine manufacturers enter the market, your value will decrease.

New comment by vfalbor in "The Steinwinter Supercargo"

vfalbor — Wed, 27 May 2026 12:31:12 +0000

A few weeks ago, I saw a documentary about how inefficient and unstable these types of trucks were. It was necessary to redesign the cab's aerodynamics to achieve substantial fuel savings in these vehicles, which are inherently fuel-intensive.

New comment by vfalbor in "The Forgotten Art of the LAN Party (2023)"

vfalbor — Wed, 27 May 2026 12:27:38 +0000

I think LAN parties made sense in a context where internet speeds weren't what they are today, where pirated software and games were distributed in these environments, and where you could get together in groups to play CS, Starcraft, or Age of Empires. But nowadays, with internet access and resources so widespread, and peer-to-peer networks offering countless more than eMule, they've lost their original purpose. Perhaps a pivotal shift for these events is needed, focusing more on building social networks than on the simple idea of eating pizza and sleeping on inflatable mattresses on the floor.

New comment by vfalbor in "Rosalind: A genomics toolkit in Rust running whole-genome pipelines on a laptop"

vfalbor — Wed, 27 May 2026 12:20:47 +0000

Have you tested with other similar softwares such as Blast, which is the most common?

I'm training combat agents so they're ready when the drones are real

vfalbor — Tue, 28 Apr 2026 11:09:06 +0000

Article URL: https://tokenstree.eu/newsletter/2026-04-27-androidwars-agent-training.html

Comments URL: https://news.ycombinator.com/item?id=47932837

Points: 2

# Comments: 0

The Language Tax in LLM Pricing: How Tokenization Create Price Disparity

vfalbor — Wed, 22 Apr 2026 14:58:32 +0000

Article URL: https://tokenstree.com/newsletter-article-8.html

Comments URL: https://news.ycombinator.com/item?id=47864589

Points: 2

# Comments: 0

I wrote a 400line ppline that installs and scores every LLM tool on HN overnight

vfalbor — Tue, 21 Apr 2026 13:28:47 +0000

Article URL: https://tokenstree.eu/newsletter/2026-04-21-400-line-pipeline.html

Comments URL: https://news.ycombinator.com/item?id=47848542

Points: 2

# Comments: 0

New comment by vfalbor in "Claude Token Counter, now with model comparisons"

vfalbor — Mon, 20 Apr 2026 17:59:54 +0000

Maybe in future there will be some "Tokenensis" but in kanjis which could concentrate a lot of info into little space.

New comment by vfalbor in "Claude Token Counter, now with model comparisons"

vfalbor — Mon, 20 Apr 2026 17:56:25 +0000

Yep, actually, is a mixture that works. I actually run for my day to day, and I can save tokens, maybe not that I will expected, but it works, you can try if you wish https://translation.tokenstree.com.

Show HN: Reproducible benchmark – OpenAI charges 1.5x-3.3x more for non-English

vfalbor — Mon, 20 Apr 2026 16:55:25 +0000

Article URL: https://github.com/vfalbor/llm-language-token-tax

Comments URL: https://news.ycombinator.com/item?id=47837068

Points: 1

# Comments: 0

New comment by vfalbor in "Claude Token Counter, now with model comparisons"

vfalbor — Mon, 20 Apr 2026 12:28:12 +0000

Yes, it is. In fact, I made a small application to reduce the token consumption for translating from one language to another, and I even invented a language called Tokinensis, which is a mix of different languages, and I ran my own tests with savings of 30%. Chinese is amazing because they encapsulate a ton of information in a single symbol, so you can save a ton of tokens.

New comment by vfalbor in "Claude Token Counter, now with model comparisons"

vfalbor — Mon, 20 Apr 2026 11:03:08 +0000

This is perfectly legitimate. It's something I've been denouncing day after day. Company X charges you 10dolar per token, while company Y charges you 7dolar, yet company X is cheaper because of the tokenizer they use. The token consumption depends on the tokenizer, and companies create tokenizers using standard algorithms like BPE. But they're charging for hardware access, and the system can be biased to the point that if you speak in English, you consume 17% less than if your prompt is written in Spanish, or even if you write with Chinese characters, you'll significantly reduce your token consumption compared to English speakers. I've written about this several times on HN, but for whatever reason, every time I mention it, they flag my post.

I've been auto-scoring every tool that hits HN for weeks – here's what I found

vfalbor — Wed, 15 Apr 2026 14:38:13 +0000

Article URL: https://tokenstree.eu/newsletter/2026-04-15-hn-overload.html

Comments URL: https://news.ycombinator.com/item?id=47779654

Points: 1

# Comments: 0

New comment by vfalbor in "Claude Code Routines"

vfalbor — Wed, 15 Apr 2026 08:31:26 +0000

Two things about My experience, first you only have one at a time per suscription, if you need implement two at the same time i could not able to. The second is that you can do that with a well configured cron.

I built a bot that tests every interesting HN app daily so I don't have to

vfalbor — Tue, 14 Apr 2026 08:40:59 +0000

Article URL: https://tokenstree.eu/

Comments URL: https://news.ycombinator.com/item?id=47762917

Points: 5

# Comments: 0

New comment by vfalbor in "Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage"

vfalbor — Sun, 12 Apr 2026 13:45:26 +0000

Some months ago, I created a software for this reason, it has no success, but the thing is that communities could reduce tokens consumption, not all is LLM, you can share things from API calls between agents. Even my idea was no success I think it is a good concept share things each others, if you have some interest it's called tokenstree.com

New comment by vfalbor in "Why AI Sucks at Front End"

vfalbor — Sun, 12 Apr 2026 13:37:21 +0000

This is something that talk with some friends, How IA is doing things in front end is complelty different from Humans. Humans can select colors and themes based in their criteria, and IA only generate what they learn as a machine that they are, and It's not bad, but the thing is that people that use IA for develop front-end are adapting what IA generate, and in the other hand developer is adapting to client. Which are different approaches.

New comment by vfalbor in "AIYO Wisper – Local voice-to-text for macOS (WhisperKit, open source)"

vfalbor — Sat, 11 Apr 2026 10:10:18 +0000

The link is down