News for hackers. Stuff that matters.

gioscarab

Re:OpenAI is well positioned to fast-follow Jev on Tuesday September 22, 2026 @02:06PM (#49805608)
The next step is to rediscover Eliza :)

I did so a month ago, I developed a deterministic agent framework that works with a set of predefined intents, it is instantaneous and fully deterministic.

It works thanks to FlintParser (https://github.com/gioblu/NPC-Forge/blob/main/src/FlintParse...) which can transpile plain English to any Programming Language. IMHO this is the future of AI.

Check it out: https://github.com/gioblu/NPC-Forge

Re:Show HN: I inadvertently built an English to Bash transpiler on Sunday September 20, 2026 @02:03PM (#49778270)
Thank you! Let me know what you think if you try it out :)
Yep he runs on its own when the command is non-destructive, like checking the CPU temperature, it does ask for permission if the command is potentially destructive. I agree it is so cool, it looks sci-fi :)
Ciao, yes for now the sentiment analysis is used only to provide an emoji related to the response. In the future I would like also to influence the choices of adjectives and interjections according to the sentiment.

For now it is a bit of a gimmick I agree :)

Yeah would be a nice experiment, if you are interested to contribute to NPC-Forge please open an issue, I would be happy to discuss about that.
This is such a nice idea! I could add a fallback towards LLMs, it was present but I removed it. Would you be interested to help me implement the auto-update? I must admit, the LLMs are very useful for this kind of work. I think that TERMY's design is now feasible BECAUSE OF the availability of LLMs. They make the dataset development feasible.
Thank you very much for the link.

WOW! With that dataset the capabilities of TERMy could be vastly extended!

Thank you.

tealdeer just shows you a cheatsheet, termy can effectively take a prompt and execute a command, example:

$ termy create file test.txt and write Hello

TERMy | template match | Confidence: 100.00%

Thinking: Ok, I am asked to create the file test.txt.

echo 'Hello' > 'test.txt' && termy_set_context 'active_file' 'test.txt'

Description: Writes Hello in file test.txt.

Response: Affirmative

Now that I think about it, I should let TERMy use tldr...

I tried functiongemma, it is for sure faster than those models, the problem is that is not reliable enough for a terminal assistant. I would say that no LLM is good for a terminal assistant, if you take into account the operational cost and the risk of damage. Even if it fails only 1 time out of 10 becomes useless. That's why I developed FlintParser!
The dataset is here: https://github.com/gioblu/NPC-Forge/tree/main/npcs/termy/dat...

I hope the community will help me to enhance it :) it is just a proof of concept for now

Warp uses LLMs so it is slow and prone to hallucination. Using very colloquial terms TERMy is more or less a calculator that knows english :) so it can run on your CPU and respond instantly! The difference is that it can only answer predetermined responses (with optional arguments) this makes it useless if you need to generate text, but makes it safe and predictable for a use case like a terminal assistant.
Hi, I am the creator, feel free to ask any questions :)

What do you think about it?

Show HN: TERMy – A fast terminal assistant that does not use LLMs

https://github.com/gioblu/NPC-Forge/blob/main/docs/development.md

I love research and development, you may have heard of me because of PJON (Padded Jittering Operative Network). It is a network protocol I started developing in 2010, which was recently implemented in silicon by the ETH Zurich university thanks to the research of Pius Sieber.I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything...

( Read More... | 45 comments | on HN )
Re:Show HN: TERMy – Deterministic terminal assistant for Linux on Thursday September 03, 2026 @12:25PM (#49552647)
Here a video of TERMy in operation: https://www.youtube.com/watch?v=qeIp0xePLBg
To be clear, the word "human" is used determine who can use the software because I am convinced that, when a company, institution, organization or corporation is created, it has its own intelligence, means and interests that go beyond and above the interests of human beings.

Many are scared of the singularity, thinking that general artificial intelligence out of human control is the greatest threat for humanity.

I am convinced that the greatest threat for humanity is more probably just a corporation operating to achieve its own interests.

A one man company consulting another would apply the software for commercial purposes. Commercial use is not comtemplated by the license. The one man company should contact me and buy a different license.

I am not sure about: >"This is my project, you can use it if you want. If you want a patch added, pay me. If you want support, pay me."

Because if you are an experimenter asking for a patch I could be also interested in, that could help the project in any way, I could consider doing it for free as part of effort required to develop the project.

Hobby clubs could not use it because they are an organization, members of the club could use it because they are individuals playing with their hobby. Non-profit organizations could not use it.

I must say often non-profit organizations even if not producing money have strong conflicts of interest.

The idea is, let experimenters tinker with it and help you develop your idea, while at the same time exclude companies, institutions, organizations and corporations. If the software is interesting for them they can contact the copyright holder to buy a different license.

Instead of giving away for free our work to entities that may work against our own interests, we give it away for free only to people like us.

Show HN: A license designed to save the open source movement

Open Source experimenter license."You" (or "Your") shall mean an individual, human, exercising permissions granted by this License."Software" shall mean the source code, associated documentation and configuration files included in the <project name> directory"License" shall mean the conditions for use, copy, modify, merge, publish or distribute the Software as defined by Section 1 through...

( Read More... | 8 comments | on HN )
> It needs to supports, out of the box, cloud connected or wifi enabled (wireless lan connected) devices. When the physical layer of devices in the home don’t offer Wireless connectivity, hardware communication modules needs to be adopted to bridge the existing connectivity.

The protocol the OP wishes for exists already, it is called PJON: https://github.com/gioblu/PJON

Re:IPFS Local Offline Collaboration Sig on Monday March 15, 2021 @11:21AM (#26467049)
Until it ultimately relies on Amazon S3 and a commercial network provider all the effort to obtain "decentralization" looks wasted. I hope IPFS will someday run on top of protocols like PJON ( https://github.com/gioblu/PJON ). Decentralization and democratization of networking will happen from the lower end, when the network infrastructure will be ours, and we will not be forced to pay multiple corporations to temporarily store our data or get it from one end to the other. Then, IPFS may have sense.

In my opinion we should:

1. Specify new data link and network standards for decentralized networking over private and decentralized networks

2. Build the networks

3. Start to think about high level stuff like IPFS

Re:Ask HN: Is Your Spacebar Working on YouTube? on Wednesday March 10, 2021 @03:19PM (#26415636)
broken
PJON supports mesh networking too, it is open-source and free to use, check it out: https://github.com/gioblu/PJON

its address space may be beneficial (more flexible, lower overhead) for many use cases.

Re:BIPLAN looks to be 1370 times faster than Python on Sunday February 21, 2021 @08:29AM (#26213296)
>Still, a toy language...

Not sure what is the effective definition of "toy language".

>...focusing on a particular benchmark can most likely easily beat any other high-level language.

I was just curious to understand the performance difference so I have tried fib(40) on both BIPLAN and python side.

How can python be THAT slow? It is a huge waste of energy and people's time.

Re:BIPLAN looks to be 1370 times faster than Python on Sunday February 21, 2021 @08:09AM (#26213193)
BIPLAN: https://github.com/gioblu/BIPLAN is a programming language, which comes with its own virtual machine and its compiler. It is really simple and it is an early protototype, although benchmarking it looks astonishingly quicker than other interpreted programming languages like python. How can be 3 orders of magnitude quicker than python? O_O
I really need some help on real-time operative systems, the interface for windows is more or less ready, and the code should work on win out of the box, it should be rather simple to create a console program that can:

BIPLAN compile program.txt (compiles in program.bp/bip/bipl)

BIPLAN run program.bp/bip/bipl

would be helpful and fun to have it running on windows or linux.

Older »