Replies
My responses to posts across the web. (113 total)
-
In reply to: via Web
PermalinkNo, because my Fedify implementation does not support the Mastodon API Fedify also doesn’t at the source (if I’m not wrong) I could put in place the missing blocks to simulate a workaround but then I would have to maintain this against the Mastodon API changes
-
-
-
-
In reply to: via Web
Permalinknew saas idea : pay to see the horizon in the current simulation of reality !
-
In reply to: via Fediverse
PermalinkAs if, any form of opposition to the the duopoly, wouldn’t need to be ruthless to operate in a shark tank
-
-
blog.giersig.eu
In reply to: via Web
PermalinkI want to change the logo provenance for indieweb to something better than a globe
-
In reply to: via ATmosphere
PermalinkI still have to fix provenance icon origin as you can see in the interactions below, they are coming from mastodon but are marked with a “from the web” origin, which is for indieweb not AP/mastodon.
-
In reply to: via ATmosphere
Permalinkbien reçu :) résultat visible sur mon site : https://rmendes.net/notes/2026/03/15/fbb7d/
-
-
-
-
In reply to: via Fediverse
PermalinkI have not gotten any spam (yet) but I’m concerned about this too… for webmentions I built a backend moderation tooling so that I can block future webmention spam if that happens one day I can also delete webmentions (even if they keep existing at the source obviously) but for comments and other forms input I’m not sure how I’m going to proceed yet
-
In reply to: via Web
PermalinkI went and added AI usage metadata to my JSON-LD also added a AI usage page https://rmendes.net/ai/ and every posts on my blog have a easy to read/interpret AI usage transparency card;
I went this direction because I think, AI on blogs is not a blanket, its not ALL or nothing, it should be granular, per posts.
And just because one co-draft a tutorial or long form with an AI does not mean or equal AI generated.
I posit that this approach will be implemented in different ways but will ultimately be common in just a few months/years
-
-
In reply to: via Web
PermalinkI’m reading your posts about your experimentation with Claude Code and I have a few suggestions :
- how do people use it with large project ? by setting it up properly, claude.md at the user level and repo level is bare minimum (these are two very different claude.md with different purpose)
- Use Obra Superpower to plan/execute dev tasks (literraly change the way claude behave)
- Do not “chat” with it, investigate code base, plan, execute and carefully augment the claude.md of the repo with carefully chosen information you want it to load in its context each time you launch claude in that repo
- your repo claude.md is not for humans or for documentation, its for claude; do not let it grow indefinitely, you’ll poison your context window
- If you really need to give specific documentation know-how to claude, build a separate repo only for documentation, generate documentation from code base and then launch agents to fact check it, configure your claude with a hook to update documentation or claude.md when necessary after each dev phases
- If you have to repeat more than 2 times an information of context about a code repo to claude, this information should be stored in claude.md
There is so much more to say but…perhaps I should write this down on a blog post :)
-
In reply to: via Web
PermalinkThis is a very cool idea ! imagine a Grafana dashboard for Fedify with all the important metrics !
xoxo.zone
kevquirk.com
sauropods.win
mastodon.social
bsky.app
indieweb.social
social.coop
fosstodon.org
manton.org
daveverse.org
hollo.social