Hacker News Reader

trilogicon Jan – Open-Source ChatGPT Replacement

But it needs internet connection to work first time and has telemetry on it. It is still a nice app though. HugstonOne has an open source version also but the features kept getting stolen (i:e first openai with the memory feature then deepseek with the dragsplit in gui no credits given). Make jan great again, take off telemetry and make it fully offline.

trilogicon The EU is about to sell our most sensitive data to the US for visa-free travel

I do not agree and do not consent to give away my biometric data. With which authority is this happening? Some are about to loose their job.

trilogicon Ollama: All Aboard Open Models

That´s the whole point, once you take the money, not your decision anymore. We also received good offers at Hugston (over 3 million dollars) to buy our decision making but we didn´t take it. It is not easy to deal with the team and the perhaps but we kept our principles. Nothing against investors, but once they "invest" they are all over your neck and board of administrators weekly. There finishes the joy/innovation and starts the unpleasant route. We will go out with the new version of HugstonOne (in the coming week) which is way superior and very powerful to everything worldwide right now for Local AI and Privacy and features, but users are 100% ín control, NO TRICKS.

trilogicon Ollama: All Aboard Open Models

How did they raise that amount of money if they are so hated, I see only bad comments everywhere about ollama. Not a fan of them myself, but they played a good part in local ai since the beginning. The investors screw everything: Ollama announced an $88 million financing on July 9, 2026. The named participants were:

Investment firms and organizations

Benchmark — represented by Peter Fenton Theory Ventures — Tomasz Tunguz 8VC — Alex Kolicich Y Combinator Garage Capital Pace Capital 49 Palms GTMFund

Individual investors

Solomon Hykes — Docker founder Aaron Katz — ClickHouse CEO Spencer Kimball — Cockroach Labs co-founder and GIMP co-creator Quinn Slack — Amp CEO Marianna Tessel — Cisco board member Michael Montano — former Twitter head of engineering Other unnamed angel investors >like lmstudio and google/alphabet maybe!

Investors are not free

trilogicon OpenAI reduces Codex Model Context Size from 372k to 272k

That is a good point actually (this is how we at Hugston measure tokens, in bytes). 270k tokens should be around ~1100kb or 1 MB, so not really enough for a serious project.

trilogicon OpenAI reduces Codex Model Context Size from 372k to 272k

Thats not even enough to read a simple codebase, how is that enough?

trilogicon OpenAI reduces Codex Model Context Size from 372k to 272k

HugstonOne increased coding context size, from 1 to 4 Million ctx

trilogicon OpenAI loses trademark dispute at EU court

This means light green to all EU tech companies using OpenAI name in their products! Even though can´t say for sure if is good or bad for a company doing that.

trilogicon Inkling: Our Open-Weights Model

You certainly cooking smth, Good Luck Mira.

trilogicon LLama.cpp Got Screwd

How is adding compulsory HTTP to CLI necessary for refactoring the code?

You realize that now the CLI needs http permissions to load a model locally. Still confused why, the server already does that by all means.

First they changed the remote downloading weights in server. Then they approved and merged claude code snippets. Now mandatory monitoring.

Everyone has a price

trilogicon LLama.cpp Got Screwd

We are heading towards a closed and monitored system, better said a proprietary one soon. Get the last genuine llama.cpp build before to late b9925.

The CLI now asking for access to load the model?

Here the change that screw everything:

b9927 @github-actions github-actions released this 17 hours ago b9927 c264f65 Details cli : move to HTTP-based implementation (#24948)

cli: move to HTTP-based implementation

wip

working

remote server ok

cli support router mode

Co-authored-by: Piotr Wilkin ilintar@gmail.com

case: router with only one model

Apply suggestions from code review

Co-authored-by: Piotr Wilkin (ilintar) piotr.wilkin@syndatis.com

remove outdated comment

use destructor instead

add ftype

cli-view --> cli-ui

pimpl

no more json in header

nits fixes

also show model aliases

Adios llama.cpp.

trilogicon Biohacker seeking immortality afflicted with incurable 'stomach eating' disease

What he did is filtering through all the noise and getting straight to the point, doing what he believes no one else has done and leading by example. We can argue about ethical and non conventional ways ofc that need to be optimized. The noise like this post comments will always be there, but doesn´t really matter actually :). Then being jealous or "skeptic" because he made some money out of it, it is nonsense. An example: most people die because vitamins, minerals, amino acids deficiency every day (an easy one is vit D). How is that bad, Informing and providing them with the solution? (ignorance at it´s finest). Reminds me of how ancient people was burning a "witch" cause knew how to heal with herbs.

trilogicon Biohacker seeking immortality afflicted with incurable 'stomach eating' disease

There is nothing more valuable than doing what you believe and love in the life. Especially when doing no harm, furthermore trying to solve a great problem with great benefits for society.

Is incredible but understandable, that many don´t get it.

trilogicon Google Books (or similar) all book scans – $200k bounty (2025)

Libgen and similar are more alive than ever with an extended botnet growing weekly. The "googlers" indexed framework is shrinking everyday, so users wont find it in those search engines easily, also it is hard to keep up with a good storage considering price trend last 5 years so the botnet and torrents are some kind of solution I guess. (We for instance are considering to use the old taping system, cause is at least a viable alternative.

trilogicon Google Books (or similar) all book scans – $200k bounty (2025)

Who is behind Annas archive, there is a lot of english speakers involved in the team and forums! Anyway as long as buying isn´t owning no issues here.

trilogicon Qwen-AgentWorld: Language World Models for General Agents

https://hugston.com/news/qwen-35b-agentworld-insights

https://hugston.com/models/hugston-qwen-agentworldq4-k-m

trilogicon Munich 1991: The Roots of the Current AI Boom

I see you need me to spell it for you. "AN INVENTION MADE IN EUROPE, PAID WITH EUROPEAN TAXPAYERS MONEY, NEED TO BE MONETIZED BY EUROPE". This way everyone gets credit and the research can stay open and available for benefits to everyone.

I would continue explaining further but you can´t distinguish sarcasm :/

trilogicon [dead]

Can download the skills or the whole pack at: https://hugston.com/enterprise.

Available for ~24 hours

Enjoy

trilogicon Mistral OCR 4

Mistral keeps reminding us that doesn´t just brew great coffee, they can build great AI too. Hats off to the team. Mistral O.C.R. (Only Cool Results)

trilogicon Claude Tag

>Set a limit on your organization’s monthly spend

A tiny detail...

trilogicon Munich 1991: The Roots of the Current AI Boom

Right, is totally fine to create new inventions, but let others take credit and financial benefits. It is our duty to protect and get the benefits of European inventions, especially the ones financed with public tax. Open for everybody means benefits for everybody.

trilogicon Munich 1991: The Roots of the Current AI Boom

> it is easy to forget that the foundations of this trillion-dollar industry were laid down over 30 years ago in Munich

Yes is very easy to forget, cause the trillion is not being made in Europe. If it was really conceived in Munich (like the maps that got stolen also), it show how incompetent is Europe to keep it´s technology and protect European companies.

It is painful to read this article.

trilogicon OpenAI is a non profit after all

With a ~40 billion usd hole (netloss) Openai keeps it´s word by staying a nonprofit company

The supposed "leak": https://arstechnica.com/ai/2026/06/leaked-financial-docs-sho...

Although I feel kind of sorry, they played a fundamental part for AI world.

trilogicon Japan and Korean Stock markets incredibly/dangerous growth

https://www.cnbc.com/quotes/.KS11 from 2900 to 9000 in one Year (3x profit) https://www.cnbc.com/quotes/.N225 from 38000 to 71000 in one year (2x profit)

Isn´t this suppose to grow in relation/ratio to National GDP? Are they growing so much for really or they are trying to keep up with money printing? There is no correlation markets/inflation the last year so what the heck is happening, are they doomed or they know smth we don´t?

Imagine that for the pension funds, they just got a boost of 200-300% of their entire lifetime savings, where is this money coming from, who is paying the bill? Who is throwing trillions to that market?

trilogicon Qwen-Robot Suite: A Foundation Model Suite for Physical World Intelligence

This is brilliant, the very future of humanity and huge market share for the next 30 years. The cards on the table too early can be a mistake. With Qwen background this can be mass production like 1 Million units/year in the next 3 years. Think of excavators but in minisize for human use. OMG Europe look at this and take note, every industry dream, the robot suit. It will take over the car market by X10 fold in the next decade. Please Europe get on this fast.

trilogicon Running local models is good now

I use HugstonOne (that backend a personalized version of llama.cpp). Implemented it´s own double layer memory that recall the full or partial previous session/file with an ON/OFF switch (which picks up where left off in CLI or Server or both same time) and another that reads back a % of current tab if memory switch is off doing checkpoints every certain tokens, summarizing and referring back to it when needed (recalled by certain logics). There is more to it when involving local RAG (making it tripple memory layer) but thats a long story.

About the harness depends on for what you need it, but basically for a universal unit of measure, Harness is multilayered and logic and domain specific dependent. I would definitely include Type of Hardware, Model parameters/knowledge, Model Intelligence, Model size/context, type of conversion, type and quantization (models comes with some default tools), but adding your (domain specific), skills, tools, memory, logs, security, Rag, Online search... (which as scary as they sound are mostly simple logics in a txt file, like if this do that).

The full pack is Harness 10, every missing thing lower the harness score.

To answer to your question I would definitely recommend smth like HugstonOne (or anyway llama.cpp CLI) with Qwen 3.6 35B finetuned/distill (deepseek 4 or claude 4.7) with none of the current coding agents out there that are screaming internet connection and proprietary API and data collection. DO this, if you can find a tool that you can download and choose a local model (of your choice in whatever folder locally) and load it ready for inference without any need of internet connection that is the tool you should aim for. Right now there is none out there.

trilogicon Running local models is good now

I also confirm that local inference is on par with proprietary cloud services (with a bit of local setup, simple agents.md and some utils skills). This local models come with tools, that's mind blowing, considering that some months ago we had to .md tools ourselves. What makes a model worth even more is "Memory". We implemented that long ago. Last time I used proprietary services was 3 months ago, don´t really need it, my subscription is going blank.

Gerganov, hope you will consider developing further the CLI cause we suffering with the server.

trilogicon I Fired Google

Google is following facebook, they got an expiration date, born together, expired together, RIP

https://futurism.com/artificial-intelligence/google-ceo-sund...

trilogicon Europe Wants Digital Sovereignty. 2,165 Polish Organisations Show the Gap

Hugston.com 100% European and dependency free. Do not rely in external dependences, they can shut you down whenever they want, besides that a dependency is unsafe and collecting your data anyway.

Europe is still sleeping, and heavily relying on others technologically. Wake up, is a dependency for gods sake, DE PE NDE NCY.

trilogicon [dead]

Original work: https://huggingface.co/lordx64/Qwable-v1

You can find iq4_nl also here: https://huggingface.co/Trilogix1