Hacker Newsnew | past | comments | ask | show | jobs | submit | _boffin_'s commentslogin

Does not work for Claude, at least for me and I put it as the system prompt

For me it works at first but Claude models forgets it after some prompts, despite only using like 100k tokens.

Your best bet is to use hooks and inject it after every file edit / response by first running the content through haiku and asking if it is asd 100 ste.

It burns more tokens but is the only way to get tolerable text.


Doesn't it just get attenuated and start ignoring those commands?

The hook sends the text to another agent/context with a request to validate and return a good or bad + reason response. Every request is a fresh context.

https://code.claude.com/docs/en/hooks-guide#agent-based-hook...


Yes but Claude starts ignoring messages when it keeps getting told the same thing over and over.

I don’t think system prompts are particularly reliable way to do much at all. It’s better to put it as a hook after each response, or a skill at least so you can trigger it at will if you don’t want it everytime.

Do you think they're unreliable based on the position in the conversation or other factors?

Anthropic has probably RL’d the system prompt into nothing because of their fear of the user being able to control the model. If it listened to you about the slop language, it might listen to you if you asked it to help you with no-no tasks.

It does work, you however have to put it into every single prompt in which you didn't want a rubbish response

Literally every one, even 1-2 prompts later it starts to go back


Any relation / inspiration to GLiClass?

i really thought "Apple Intelligence" is the addition of data into Knowledge.db, but i guess not.

Oh... amazing. just had a vision of being able to be in a meeting and talk through an User Interface design / review, while in a zoom meeting or whatever.

...i like.

---

- Design system / Component lib

- Live view of what components, tokens, other things... on the left side of the screen.

- You're in the meeting and talking while talking and transcribing and doing the full duplex voice. You say, "Find what tables and customizations we have available" and the list starts to filter to tables and customizations.

- "Let's add that table to the page; left side; 3/4 width of page. Headers should be static for vertical scroll, ..."

- The table is added to the page.

- "Nah, i don't like it. Let's change that table component to have larger headers..."

yes, i like--let's see what Astra Pro pops out with.


The problem with that is that it only works with simple, least interactive UIs. Each new UI a human will be presented needs to be learned to be ised effectively otherwise a user will be lost.

Having said that, imo, Gen UI only makes sens as a presentation layer - not controls. Unless LLM will be using a set of very well defined and homogenic components like table, forms, small widgets.


> The problem with that is that it only works with simple, least interactive UIs.

I believe that's incorrect. you can define the architecture to be able to provide data based on information from the frontend and the components just need to define a query and data structure or something -- will have a prototype soon


One thing I’ve done is a few books and check what branch / work tree user is on. Allows for more fidelity than even this. Works quite well.

I just wish they allow for getting inside subscription pricing vs outside subscription pricing easier


I think this actually might be one of the best ways to train people to use AI. I can see this honing people's prompting abilities and expressiveness, along with constraints and desired outcome.

Wild the possibilities


One thing I don’t get with a lot of these agents.md and other skills are… why not throw as much mechanical checks and other stuff at the repo to constrain as you want instead of asking a non-deterministic agent (squishy or non-squishy) to maintain it.

With the mechanical routes, we get checks, failures, and so much more. A bit wild to me.

Make an agent operate within defined constraints and yell at it when it doesn’t.


Do both. Instructions help avoid the first pass from making the same mistakes.

> Make an agent operate within defined constraints and yell at it when it doesn’t.

And tell it what the constraints are.


Check out the book called, The Logic of Failure. I think you’ll like it


Two other great books on failures in inevitably complex military operations are:

1. Command in War (1985) by Martin van Creveldt. He dissects may complex but common military failure causes up to the Vietnam War.

2. Team of Teams (2015) by Stanley McChrystal that is focused on what he and teams learned in Iraq but extrapolating to most organizations.


Did love Team of Teams. Need to check out the other


van Creveld is correct spelling.


Nice. seems like this converges on something i built called https://Tangents.chat, specifically the "Context complier", which can be seen here (https://tangents.chat/demo) (click Context in the top right after entering the demo).

Looking forward to looking more at ThoughtDAG.

Visual: https://i.ibb.co/NRHSFrg/tangents-context-complier.png


Thanks! I don’t know if ALL markdown is going to be implemented or not yet, but not out of consideration.

Question: anything that caught your eye in regards to this project?


No, it's working fine.


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

Search: