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

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

Thank you.

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

What do you think about it?

I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything else being built today, TERMy does not use embeddings, machine-learning or LLMs. It runs on the CPU (even on a Raspberry Pi Zero) both in the terminal or client-side in a browser tab and responds in milliseconds. It is a cynical but very knowledgeable Linux terminal assistant that translates your natural language into shell commands without relying on a single artificial neuron.

I had a chance to focus for 2 months on my personal projects since early July, during the strange times of AI price hikes and the end of subsidized tokenmaxing. I was curious to see if I could develop from scratch a terminal assistant capable of handling simple natural language requests. I have a bad memory and got used to ask to copilot "activate the virtual environment" or similar trivial operations spending a non negligible sum every month. I started thinking, maybe I can do something to make my workflow more efficient? Do I really need trillions of parameters to accomplish those tasks?

How it Works

When you type a prompt, it goes through a lightweight NLU pipeline written in ~1000 lines of Python that implement the following steps:

1. Strip expletives, interjections, encouraging, discouraging and thanking words (remove noise)

2. Sentiment analysis

3. Exact Match (very fast)

4. Template Match (slower)

5. Probabilistic Match (even slower)

Step 5 relies on:

1. IDF (Inverse Document Frequency) to identify rare words.

2. BOW (Bag Of Words) to accommodate word inversions.

3. IDF weighted Levenshtein to safely handle typos.

Permission gating is hardcoded into the dataset and enforced for all potentially destructive commands, so it's inherently safer than letting an unpredictable LLM run wild on your machine.

- TERMy in operation: https://www.youtube.com/watch?v=qeIp0xePLBg

- Variance and typo tolerance: https://www.youtube.com/watch?v=tQvGDk6fkk0

- Copilot integration: https://www.youtube.com/watch?v=Wzzouhq2a8A

- Advanced features: https://www.youtube.com/watch?v=qeIp0xePLBg

- Source Code: https://github.com/gioblu/NPC-Forge

Comments URL: https://news.ycombinator.com/item?id=49562219

Points: 196

# Comments: 44

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.

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.

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

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.

"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 directory

"License" shall mean the conditions for use, copy, modify, merge, publish or distribute the Software as defined by Section 1 through 3 of this document.

Experimenter's License

Copyright

Permission is hereby granted to You, free of charge, the rights to use, copy, modify, merge, publish or distribute copies of the Software, subject to the following conditions:

1.Use, copy, modify, merge, publish or distribute the Software only for experimental or educational purposes.

2.Companies, institutions, organizations and corporations don't have the right to use, copy, modify, merge, publish or distribute the Software

3.THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. YOU ARE SOLELY RESPONSIBLE FOR USING, COPYING, MODIFYING, MERGING, PUBLISHING OR REDISTRIBUTING THE SOFTWARE AND ASSUME ANY RISKS ASSOCIATED WITH YOUR EXERCISE OF PERMISSIONS UNDER THIS LICENSE.

Comments URL: https://news.ycombinator.com/item?id=30742650

Points: 1

# Comments: 8

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

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

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