crashabr

Pretty cool. I have my own setup for presentations, and I also use revealjs, but I made the choice to have the content be sourced from a markdown to be able make presentation contents as indexable and reusable as any other content produced by my team.

How does it compare with https://github.com/agent-of-empires/agent-of-empires

I'm following a startup who does just that: https://www.moment.dev/docs

It's still early stage, but I love their pitch so I'm following them with fingers crossed.

I will never be this man again

Any examples of other impressive Ren'py showcases?

I don't follow this system per se, but for me the unlock was to build a a map of my life from the get go, following the PARA system (projects, areas, resources, archives). It has been a game changer because now I willingly take more notes, snip more quotes etc as it's never a struggle to know where they fit.

I also use Logseq, not Obsidian, which encourages a journal like workflow. Specifically, using templates is almost like a simple interactive prompt: /template > decide if it's work project or personal area or whatever > get a pre-filled note starter, with suggested tags (I delete the ones I don't need rather than think about the ones I have to add) .

It's just so easy.

Once you got the habit of writing down a lot of stuff, and putting them in the right bucket, a lot of things become easier, and LLMs make some of those even easier.

The visual cleaning idea is really interesting. Would you mind sharing more details?

I wonder how well this would work with dance videos.

Honestly not sure what I would be using this for when there's Claude remote control? Is it because you can script the telegram bot to send messages at regular intervals? But Claude has a /loop as well, so I'm still confused.

No, the tool building looks very sophisticated and powerful and I love that it hinges very much on the new era of building your own custom tools with the help of agents. The live collaboration on top of md files is also exactly what I was looking for!

If you're saying that Logseq on steroids is what you're aiming for, then, my immediate feedback would be to emphasize more: - the writing experience: at the end of the day, writing and taking notes will be the most common activity - the file organisation: tags, templates, media files, does it do the basics? - the sharing and access mechanism: can I easy share a doc with a partner / client?

Those are the basics of daily business tasks for my consultancy, and so the first thing I'm looking for. I really wish to get off Google drive, but those points need to be solved for that to sound feasible.

As for the tool building it looks very powerful, but the first example you presented (on-call dashboard), was a bit too much from the get go to wrap my head around the building blocks of your system. I've been building custom tools/wrappers of varied complexity on top of markdown for my team, from a custom revealJS skill that follows our design guide, to a form builder to a project/client DB that wraps duckdb (for yaml frontmatter parsing) with a semantic layer. I've watched your intro video but I'm still not sure whether your service would help me more closely integrate those tools to my company's knowledge base or not.

But once again, if your vision matches your tagline, then I'm really looking forward to hear more from you

You have an amazing tagline. This is the first time I read a tagline and thought: this is exactly what I was looking for.

But the product seems much more narrow than an actual tool run the whole business in markdown. I was hoping to see Logseq on steroids, and it feels like a tool builder primarily. I love the tool building aspect, but the fundamentals of simply organizing docs (docs, presentations, assets etc, the basics of a business) are either not part of the core offering or not presented well at all.

I love the idea of building custom tools on top of MD and it's part of my wishlist, but I feel little deceived by your tagline so I wanted to share that :)

Is it possible to link/wrap several skills together? I haven't managed to get Claude to react to a reference to another skill within a skill.

Looking forward to try this with my students. Thanks!

Set it up and never managed to have it work. Only thing it did was renaming my sessions on my main cc instance. Mobile did nothing, not even an error message.

This is broadly how I worked when I was still using chat instead of cli agents for LLM support. The downside, I feel, is that unless this is a codebase / language / architecture I do not know, it feels faster to just code by hand with the AI as a reviewer rather than a writer.

Would that book be useful as a reference to introduce data journalism students to AI? I'm less interested in the basics of using the API or claude code etc than best practices for workflows dealing with unstructured data, entity extraction, automated pipelines (with evals)? Although I do have some decent workflows around this I'd be interested in reading from someone who lives and breathes this kind of work. Pure data analysis to me is also something where I haven't found a good bridge between the current "generate a python script for me that I'll double check" paradigm and the spreadsheet centric world of most data journalists.

What's the hook for switching out of plan? I'd like to be launch a planning skill whenever claude writes a plan but it never picks up the skill, and I haven't found a hook that can force it to.

Could you share your setup? Also a logseq fan here

Would you be able to share more? I lead a tiny non-profit org doing data literacy mentoring and I've been meaning to move more of our process docs to Logseq. Although I probably don't need a tool of the level of sophistication of usm.tools, I could take inspiration from your core ideas for our homegrown system.

one is celebrated art, the other is virtually unknown and at best 'one among many baroque northern-talian painters'.

Who claims that 'baroque northern italian painters' are not artists? If anything, an unknown painter is much closer to art with capital A than Banksy, in the traditional hierarchy. So this is a weird framing.

As for time, this is both time taken to create and time spent practicing to reach a certain level of artistry. A speed painter is still an artist, and they reached their speed not by using an AI shortcut but by spending long hours practicing.

The underlying question is how do we tie art and legitimacy: society has always tied both, which is why we have institutions tasked with assigning legitimacy (museums), a hierarchy of art forms where the longest lived are seen as superior (painting over photography), and artists gain prestige not from a single art piece, but from a consistent production of works that are tied together by a shared identity.

On the other hand, a lot of the "pro" AI art discourse I've seen often boiled down to attempts to disconnect art from legitimacy. That's a tough hill to climb.

I've never fully understood where Outlines fit in the stack. Is it a way to create a structured output API similar to the ones big providers have? Have you looked at something like BAML?

After your comment I tried to do something with my phone but tmux + claude code is definitely not great on mobile though the main view of aoe works decently.

I'm setting up a small orchestration around zellij (I have almost no experience with tmux, so I went with the "modern" alternative), upterm and qrencode that allows me to 1) generate a claude code instance in a persistent session 2) make it controllable remotely via upterm 3) scan a qr code to copy the upterm server's ssh url on my phone so that I can paste it in termux.

I wonder if it would be more ergonomic to connect to the aoe window on my phone for when I have more then one claude code session to keep track of. I'm not against switching the zellij part to tmux.

I like delivering value

I understand where comedians get their source material now.

I've been waiting for Logseq DB to come out to replace Google docs for my team. So your offering is interesting, but

1) is it possible to use Obsidian like Logseq, with a primary block based system (the block based system, which allows building documents like Lego bricks, and easily cross referencing sections of other documents is key to me) and

2) Don't you expect to be sherlocked by the obsidian team?

This is the ultimate cope out: taking technology as a singular entity that evolved outside of human control and is simply commented on by passive observers who are simply "pessimist" or "optimist" about it instead of people whose lives are meaningfully impacted by it.

The trick to do so is to flatten human experience under the determinism of "efficiency" (which you euphemistically called "quality of life"). This way "optimists" can dismiss nuanced oppositions to a lack of regulations as "luddism" and fold together anti-vaxxers and AI skeptics, as if those are the same people, with the same motivations or arguments.

This also conveniently distracts from the fact that technological pessimism exists as a contrast to periods of technological optimism, which helps evade the question of what changed: after all, pessimists aways existed, as your link shows.

I would suggest unfolding the "pessimist" reductionism and questioning why AI skeptics are not stem-cell skeptics. This will probably help avoid arguments that sound very much like "the end justify the means".

I would recommend re-reading The Ones Who Walk Away from Omelas as a companion story then. Maybe you'll get to underhand techno-pessimism as something more than the the result of people "forgetting the incredible technology that makes their quality of life real".

The concept seems trivial and widely used by many existing bloggers (and the default for most media outlets) so I feel like I'm missing something.

Looks great, and it has some features and polish that I would love Logseq to have natively, but overall I prefer the customisation potential of logseq with tags, templates, block refs etc.

I've been wondering if it was a good replacement for the playwright mcp, at least for chrome-only testing.