Hacker News .hnnew | past | comments | ask | show | jobs | submit | esafak's commentslogin

It does know: it wants to be everything -- they remind you in every ad!

Anybody used this Agentica of theirs?

This is routine. We have Gemini (which is not our coding model) review our PRs and it genuinely catches mistakes. Even using the same model as the creator, without its context to bias it, would probably catch many mistakes.

You're joking, right? A hundred million people died in those wars.

“Mr. President, I’m not saying we wouldn’t get our hair mussed. But I do say no more than ten to twenty million killed, tops.”


I get it for open source projects but at least use something nice like depot.dev for commercial ventures.

These products maximize revenue through engagement with advertisements. The outcome is built into their business model.

How can it be obsolete? Maybe if you only have toy data you picked to write your blog post. Companies have gigabytes, petabytes of data to draw from.

For longevity, which is a consideration in such a project, one might prefer something based on Markdown files, like https://github.com/Linbreux/wikmd to Mediawiki, which uses a database. Then again it does support sqlite, which is open source, so it is not a big deal.

> ... lets focus on how we can augment and empower the existing workforce.

That is a nice sentiment but not what the AI companies are out to do; they want your job.


What problem does this solve?

can be used for syncing multiple independent sw components or Docker containers going through large datasets needing to coordinate,where state transitions are hard to track,behavior becomes implicit over time

This ought to be explained in the repo; "intention" and "pulse sets" are not technical terms that will be familiar to anyone. I would start with the problem you are solving, and explain how you solve it better than the existing solutions.

totally agree - shall be showing that demo soon - you are right — that’s a gap in how I’ve presented /formalized it so far. A more concrete way to describe the problem: In many systems where independently developed components need to coordinate (e.g. services processing data or running in containers), the logic that determines when something should happen ends up being: spread across code implicit in assumptions hard to inspect or debug over time

What I’m trying to explore here is a different approach: make the conditions for execution explicit in the message itself; So instead of: components calling each other or relying on shared workflow logic they react to explicit state carried in messages. I’m working on a small runnable example to show this more concretely — I think that will make the idea much clearer than the protocol description alone.


Here is a simple demo to illustrate the scenario how iptp can play a role when the processes are distributed , this demo puts the idea in a single process though - https://github.com/spicecoder/iptp-pipe/tree/c0945090864fae3...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: