I find vibe coding similar to visiting a country where I don't know the local language very well.
Usually that requires saying something, seeing if the other person understands what I'm saying, and occasionally repeating myself in a different way.
It can be real tiring when I'm with friends who only speak the other language so we're both using translator tools and basically repeating that loop up to 2-3 hours.
I've found the same situation with vibe coding. Especially when the model misunderstands what I want or starts going off on a tangent. sometimes it's easier to edit the original query or an earlier step in the flow and re-write it for a better result.
Depending on how long someone's been in the industry it's more a question of if, not when, an outage will occur due to someone deciding to push code haphazardly.
At my first job one of my more senior team members would throw caution to the wind and deploy at 3pm or later on Fridays because he believed in shipping ASAP.
There were a couple times that those changes caused weekend incidents.
Apologies for not reading all of your blogs on this, but a follow-up question. Are models still prone to reading these and disregarding them even if they should be used for a task?
Reason I ask is because a while back I had similar sections in my CLAUDE.md and it would either acknowledge and not use or just ignore them sometimes. I'm assuming that's more of an issue of too much context and now skill-level files like this will reduce that effect?
Skill descriptions get dumped in your system prompt - just like MCP tool definitions and agent descriptions before them. The more you have, the more the LLM will be unable to focus on any one piece of it. You don't want a bunch of irrelevant junk in there every time you prompt it.
Skills are nice because they offload all the detailed prompts to files that the LLM can ask for. It's getting even better with Anthropic's recent switchboard operator (tool search tool) that doesn't clutter the system prompt but tries to cut the tool list down to those the LLM will need.
Can I organize skills hierarchically? If when many skills are defined, Claude Code loads all definitions into the prompt, potentially diluting its ability to identify relevant skills, I'd like a system where only broad skill group summaries load initially, with detailed descriptions loaded on-demand when Claude detects a matching skill group might be useful.
There's a mechanism for that built into skills already: a skill folder can also include additional reference markdown files, and the skill can tell the coding agent to selectively read those extra files only when that information is needed on top of the skill.
I've started regularly visiting a couple coffee shops in Tokyo whenever I go there and I'm on first name basis with the owners/managers, whereas if I go to the same shops in the SF Bay Area more regularly it's rare that anyone recognizes me.
I definitely prefer that neighborhood coffee shop feel and at least shops I go to near home don't have that. Even the smaller ones with similar amounts of business and number of employees as the ones in Tokyo.
It's still easier to turn around a ring than to fiddle with a a phone. And more legal as well, no laws against rotating a ring while rinding your bike. That's fully haptic, no is drawn from traffic for that.
I'd be curious what happens if you're the kind of person who wears a ring a bit more loosely and/or has slippery skin.
That button isn't always going to be facing your thumb. Maybe you rotate it back with your thumb? Or you need to use your other hand anyway to rotate it?
I have an electric water boiler like that also. I have to be very mindful to press a button to turn it off if i return it empty to the induction plate/holder otherwise it starts clicking and beeping and freaking out.
Usually that requires saying something, seeing if the other person understands what I'm saying, and occasionally repeating myself in a different way.
It can be real tiring when I'm with friends who only speak the other language so we're both using translator tools and basically repeating that loop up to 2-3 hours.
I've found the same situation with vibe coding. Especially when the model misunderstands what I want or starts going off on a tangent. sometimes it's easier to edit the original query or an earlier step in the flow and re-write it for a better result.
reply