News for hackers. Stuff that matters.

dmilicev2

I believe so, sounds logical, yes. I haven’t measured it across LLMs to tell you if there is more/less overhead, confusion, hallucinations, repeated mistakes etc..
I feel like there should be a consistent protocol, an industry standard for interacting with AIs, I do see value in it, however, as you said, it doesn’t seem like there’s value in turning the entire web or everything we can think of into an mcp server.

At least not at the moment, and perhaps it will stay that way. Its logical to think that LLMs will always be more expensive to run vs a simple web or shell script for a specialised purpose.

Arguably you can drop an API or a local script for that AI to consume, but I do see benefits of having it standardised for the industry as mcp if you want something to run as an infrastructure layer that’s AI agnostic.

Re:Test on Thursday May 07, 2026 @03:43AM (#48046589)
foo, bar?
Thank you Mahjabinbm, looking forward to it.
Re:Are you addicted to your AI chatbot? on Wednesday May 06, 2026 @07:25AM (#48034959)
Yes. It's a continuous and steady flow of dopamine until you run out of tokens.
Re:Multi-Agent Coordination Tax: What Two Weeks Cost Me on Tuesday May 05, 2026 @10:13AM (#48022803)
I experienced this friction. Maintenance of memory across projects, across different LLMs, is a recipe for frustration and disaster.

This MCP tool I made might help elicit desired behaviour from Turn 0: https://github.com/turnzero-ai/turnzero

Yes, and that's one of the reasons I started working on this tool: to elicit desirable behavior from AIs before turn 1. AI is still non-deterministic and won't follow instructions 100% of the time, but with this tool, I intend to narrow that gap.

Would love to hear your thoughts on it: https://github.com/turnzero-ai/turnzero

I'm not sure what the best course of action is here, but I fail to see the benefits to society if we were to set up legal entities for each AI agent at this stage.

I think the responsibility should lie on the shoulders of the individual/business that deployed the AI agent. For that, I can clearly see the benefits to society.

Me neither. If true artificial sentience is achieved, what does that say about us?
AI is not sentient, therefore not liable for its actions. It would be pointless. We ought to look one step beyond the lines of code for liability.

Unless the AI eventually passes the bar of sentience.

Show HN: TurnZero – Persistent Expert for LLMs

In an attempt to reduce cold starts in AI sessions Ive made a tool that runs as an MCP server and loads the context before Turn 0.Two things happen:Personal Priors - your workflows and standards loads once per session and persists across every supported AI client.Expert Priors - when prompt is stack specific, relevar priors inject based on semantic similarity. This is to reduce errors and...

( Read More... | no comments | on HN )