HackerTrans
TopNewTrendsCommentsPastAskShowJobs

web-cowboy

no profile record

Submissions

Show HN: MCP-Teleprompter – Stop repeating yourself to LLMs

npmjs.com
1 points·by web-cowboy·geçen yıl·0 comments

comments

web-cowboy
·2 ay önce·discuss
I'm finding counterexamples of this constantly now that I can have an agent rewrite large sections of my codebase that have been sorely needing it.

- Moving to a newer and more modern test library

- Refactoring my data layer so it's easier to read, based on years of organic changes that need to be baked in and simplified

- Porting some functionality to another language to vastly improve performance

I agree with the overall sentiment, but having an agent at my finger tips who can really crank out large-scale, involved code changes is unclogging quite a few backburnered todos lately for me.
web-cowboy
·5 ay önce·discuss
Rough spot in time to be:

- Once print newspapers were no longer a thing, even local news outlets are struggling to stay alive, and are resulting to sensationalism and entertainment as news - Corporate sponsors retain a huge influence in mainstream news (or have outright purchased it and use it for partisan politics). - "Social" media resides in (you guessed it) corporate-owned walled gardens. - Even those willing to speak out are being targeted by federal agencies

Wondering where others are finding great places to learn what's going on, what's actually relevant to me, and what I can actually do about it.
web-cowboy
·12 ay önce·discuss
As I think through this, I agree with others mentioning that "deep agents" still sounds a lot like agents+tools. I guess the takeaway for me is:

1. You need a good LLM for base knowledge.

2. You need a good system prompt to guide/focus the LLM (create an agent).

3. If you need some functionality that doesn't make any decisions, create a tool.

4. If the agent + tools flows get too wily, break it down into smaller domains by spawning sub agents with focused prompts and (less?) tools.
web-cowboy
·geçen yıl·discuss
This seems like a much more powerful version of what I wanted MCP "prompts" to be - and I'm curious to know if I have that right.

For me, I want to reduce the friction on repeatable tasks. For example, I often need to create a new GraphQL query, which also requires updating the example query collection, creating a basic new integration test, etc. If I had a MCP-accessible prompt, I hoped the agent would realize I have a set of instructions on how to handle this request when I make it.
web-cowboy
·2 yıl önce·discuss
I wanted Tim Berners-Lee's "Solid" project to be at least a partial foundation for this, but it doesn't seem to be getting traction.

Some way to "self-host" or "own my own data" isn't very possible in a world of complex system administration and cloud providers, GDPR/Privacy, etc.

Maybe solving this problem (via FOSS, hopefully) and giving people their own internet-in-a-kit could be a good way to go?

Are there active projects like this? Is it even feasible?