ArtRichards

Plug here for a python app I wrote, no dependencies. It uses a skill to maintain an index, links, archival, and works with a separate opinionated dev playbook nicely. The best part is now the docs/specs folder maintains itself. (and I can spawn a new session with all the relevant context every time)

https://github.com/ArtRichards/docs-cli

and

https://artrichards.github.io/agent-playbook-suite/blog/

Theres no guarantees. When is a dangerous word. :)

I came here to post a question, which you answered. Thanks!

I personally love Privatemode's approach. Having Jev-like speed for confidential ai use cases is a huge enabler.

I tend to think of it as reappropriating words in a different context. Since we're talking about language models, they're analogues but not as we would assign the same meaning to other humans.

I'll drop mine here, I'd really like feedback, though I guess everyone has their own by now, very few will try a new SWE skills framework.

https://artrichards.github.io/agent-playbook-suite/blog/

it works with docs-cli

`pipx install docs-cli`

I have one I started back in October last year and been improving since. Also a python docs cli to manage agent state in markdown locally.

I love reading them to see if theres a way mine could be improved, what topics they hit on, how they approach different problems.

https://github.com/ArtRichards/agent-playbook-suite

https://artrichards.github.io/agent-playbook-suite/blog/

https://github.com/ArtRichards/docs-cli

I tried setting up opencode for the server, but it just won't persist my conversations. Hows the mobile/client access on this? Claude remote works well... for Claude... but I havent seen anything comparable open source.

edit: tmux + terminal harness is my current go to

I always think of it like: let it activate whatever experts to reason/do the thing, then in the next prompt give me your explainer experts. Then, both are in the conversation history.

Yes but thanks to the soul or system or whatever (talk at the operator's level), 'layman' feels like it now tries to oversimplify!

Basically every decision or summary I now ask "Help me understand better, please explain in plain-language with examples."

Works with 5.6 sol also, when you're deep in the weeds. I rationalize this as the models attempting to compress as much into the fewest tokens, though the choice of words often doesn't make sense to me, going back to read the original after, its often there. It definitely feels like a different sort of 'Machine Language' though xD

New, smaller models can outperform the previous generation's foundation models.

What if there's a way to extract the commodity of intelligence from smaller models?

I've seen for many use cases it's well enough. :)

I wonder if this was made in the sub agent's chat? Thanks for sharing.

I saw another post today about a startup making an oven for baking bread. I feel that often the main issue lies with what you need 'the code' to accomplish.

My flow state is thinking about and understanding this: am I solving a problem that needs to be solved now, for the right person?

I created this to help me understand it (project foundations + create milestones) and then bring it to reality (ship milestones).

https://artrichards.github.io/agent-playbook-suite/blog/

They're doing some really cool stuff with Agents too.. automating software pm. it's a huge difference between this and their (unnamed) larger competitors.

Its all about retaining the context and spawning sub agents which can bootstrap quickly and accurately.

I'm interested in others dping something similar :) I included a docs cli tool in pypi to manage this context:

https://artrichards.github.io/agent-playbook-suite/blog/

This is the part I think we will see become more relevant.

I created docs-cli (pypi) to manage the index of specs as source code: the framework that goes with it will first create tests for as much as it can, so reproducability becomes the goal, not readability.

https://github.com/ArtRichards/docs-cli

https://artrichards.github.io/agent-playbook-suite/blog/

This article was a really uplifing take... Happy to see more about how awesome we can be, when we care.

Apparently there's been work to expose Meta pushing/funding this, to shift age responsibility from them and force for fine grained age data to be provided to apps.

I like using the automatic lists in soundcloud to discover new music. Often its hit or miss but it can surface some great tracks... Its intentional though, gotta have your finger on the skip track and heart...

This is exactly how I've found leads to most consistent high quality results as well. I don't use gemini yet (except for deep research, where it pulls WAY ahead of either of the other 'grounding' methods)

But Codex to plan big features and Claude to review the feature plan (often finds overlooked discrepancies) then review the milestones and plan implementation of them in planning mode, then clear context and code. Works great.

Sure would love to be able to read this...

I guess he's being a bit cheeky ;)

Is this the same Google that is preventing us from installing unapproved software on our phones?

and

> But EasyJet says it has already completed the required software update and is planning on operating its flights as normal on Saturday

Lurking for over 20 years, through my entire professional career... High School to Middle Age... Thanks Dan & HN Community

In a youtube demo, the author says he has been working on this idea for a while, and was motivated to deliver after the GIF. So, kinda? Thanks for the reference.

https://youtu.be/v9FMp5QgOvY?si=iKXJSNIuLiU5nOnj

came here to post this, but it shares a different clipboard than ctrl+c/v or something??

anyone know the differences?

What did this site just attempt to do with my certificate store?

I was looking for this comment!

That being a possible reason why certain words alleviate, they actually operate at a different level in our conciousness.