I always wondered why you even have logged out access. I'm glad I can use ChatGPT in incognito when I want a "clean room" response, but surely that's not the primary use case.
Is user base that never logs in really that significant?
I'm curious, what does your workflow look like? I saw a plan prompt there, but no specs. When you want to change something, implement a new feature etc, do you just prompt requirements, have it write the plan and then have it work on it?
I want AI to have full and unrestricted access to the OS. I don't want to babysit it and approve every command. Everything that is on that VM is a fair game and the VM image is backed up regularly from outside.
I have a pretty insane thing where I patched the screen sharing binary and hand rolled a dummy MDN so I can have multiple profiles logged in at once on my Mac Studio. Then have screen share of diff profiles in diff "windows". Was for some ML data gathering / CV training.
It's pretty neat, screen sharing app is extremely high quality these days, I can barely notice a diff unless watching video. Almost feels like Firefox containers at OS level.
Have thought that could be a pretty efficient way to have restricted unrestricted convenient AI access. Maybe I'll get around to that one day.
> I have a pretty insane thing where I patched the screen sharing binary and hand rolled a dummy MDN so I can have multiple profiles logged in at once on my Mac Studio
I have a Studio collecting dust that I've been eyeing every time my VM crashed because of Apple's paravirtualized GPU proxy not being able to keep up with things I run in it.
This sounds exactly like what I wanted to do on my Studio and didn't know where to pull the thread from.
To this day, nobody has proven any subsidization is actually taking place. The only "proof" is comparing subscription with API prices, but that's comparing two very different products. Unrestricted enterprise APIs always cost more than consumer products. Sometimes a whole lot more, so API prices don't really tell you much in terms of inference costs.
And there's a reason why Anthropic cracked down on third party harnesses - prompt caching must be very effective for cost reduction, and if you look at cache hits of CC, you'll see it's very aggressive. They even said it themselves on twitter that if your limits get exhausted sooner, it's likely something with your workflow that doesn't utilize caching as well.
If any subsidization is taking place, I'd wager it's simply light users subsidizing heavy ones. But that's nothing new.
I'd also go even further and say that you likely should never install ANY skill that you didn't create yourself (i mean, guided claude to create it for you works too), or "forked" an existing one and pulled only what you need.
Everyone's workflow is different and nobody knows which workflow is the right one. If you turn your harness into a junk drawer of random skills that get auto updated, you introduce yet another layer of nondeterminism into it, and also blow up your context window.
The only skill you should probably install instead of maintaining it yourself is playwright-cli, but that's pretty much it.
what? non techies are most at risk. There are a huge number of malicious skills. Not knowing or caring how to spot malicious behavior doesn’t mean someone shouldn’t be concerned about it, no matter how much they can’t or don’t want to do it.
I am an adminstrator of this stuff at my company and it’s an absolute effing nightmare devising policies that protect people from themselves. If I heard this come out of someone’s mouth underneath me I’d tell them to leave the room before I have a stroke.
And this is stuff like, if so and so’s machine is compromised, it could cost the company massive sums of money. for your personal use, fine, but hearing this cavalier attitude like it doesn’t matter is horrifying, because it absolutely does in a lot of contexts.
I run a small local non-profit which is essentially security hardening guide with some helper tooling that simplifies some concepts for non-techies (FDE, MFA, password managers etc).
LLMs have completely killed my motivation to continue running it. None of standard practices apply anymore
I had an issue with playwright MCP where only one Claude Code instance could be using it at a time, so I switched to Claude's built-in /chrome MCP.
In practice, I also find it more useful that the Chrome MCP uses my current profile since I might want Claude to look at some page I'm already logged in to.
I'm not very sophisticated here though. I mainly use use browser MCP to get around the fact that 30% of servers block agent traffic like Apple's documentation.
Would love if there is a way to parallelize playwright mcp using multiple agents and such, but it seems it's a fundamental limitation of that MCP that only on instance/tab can be controlled.
Chrome MCP is much slower and by default pretty much unusable because Claude seems to prefer to read state from screenshots. Also, no Firefox/Safari support means no cross-browser testing.
I was using the built-in chrome skill but it was too unreliable for me. So I switched to playwright cli and I can also have it use firefox to get help debugging browser-specific issues.
Yes this is the path I’m taking. Experiment, build your own toolbox whether it’s hand rolled skills or particular skills you pull out from other public repos. Then maintain your own set.
You do not want to log in one day to find your favorite workflow has changed via updates.
Then again this is all personal preference as well.
Create .claude/commands/ when you have well defined repeatable, multi-step actions you want to take. I have a command `/triage` where I provide it a bug report and it asks me questions to start scaffolding a work area, lookup related issues, create patches, etc.
Create .claude/agents/ when you have a narrow scoped thing that you want to happen, but not pollute the main context and have a well formed output. Also handy for reducing costs by using a different model for a class of actions you repeat often. For example, the "lookup related issues" from `/triage` is a Sonnet agent that finds Trac issues for a bug reports. Main context only needs the small list of matches and not the dozens of not relevant ones.
Create .claude/skills/ for job description like behaviors you want. For example, code reviewer or security researcher.
For any of these, install the `/plugin` skill-creator. Run `/init` if you don't have a claude.md and then ask the skill creator to help you improve the claude.md and create useful commands and skills.
I used them for repeated problems or workflows I encounter when running with the default. If I find myself needing to repeat myself about a certain thing a lot, I put it into claude.md. When that gets too big or I want to have detailed token-heavy instructions that are only occasionally needed, I create a skill.
I also import skills or groups of skills like Superpowers (https://github.com/obra/superpowers) when I want to try out someone else's approach to claude code for a while.
You observe what it does to accomplish a particular task, and note any instances where it:
1. Had to consume context and turns by reading files, searching web, running several commands for what was otherwise a straightforward task
2. Whatever tool it used wasn't designed with agent usage in mind. Which most of the time will mean agent has to do tail, head, grep on the output by re-running the same command.
Then you create a skill that teaches how to do this in fewer turns, possibly even adding custom scripts it can use as part of that skill.
You almost never need a skill per se, most models will figure things out themselves eventually, skill is usually just an optimization technique.
Apart from this, you can also use it to teach your own protocols and conventions. For example, I have skills that teach Claude, Codex, Gemini how to communicate between themselves using tmux with some helper scripts. And then another skill that tell it to do a code review using two models from two providers, synthesize findings from both and flag anything that both reported.
Although, I have abandoned the built-in skill system completely, instead using my own tmux wrapper that injects them using predefined triggers, but this is stepping into more advanced territory. Built in skill system will serve you well initially, and since skills are nothing but markdown files + maybe some scripts, you can migrate them easily into whatever you want later.
Anytime I do something as a one-off that I know I'll do in the future, at the end of the session I'll ask Claude to write a new skill based on what it did. For instance, I had to run some queries on Azure to check the logs for certain output and for the frequency of output. Did it once in a session and then had it write the skill for it. Now I can just run the skill whenever I need that data and it pulls it for me.
First, this has been going on for a week now and Anthropic support was gaslighting people, saying nothing has changed. Well, obviously it has, they said it now. Additionally, Anthropic saying weekly limits are unaffected is also a lie. I exhausted 37% of my weekly on the first day when this started on Monday. This has never happened before. So this is two lies in a row.
But now the bigger issue - what does Anthropic expect me to do when I'm out of quota on day 1 of the week? Emphasis on me having a lot of free time without access to claude.
There can only be 3 options:
1. I'll buy more $200 subscriptions from a provider that I've caught lying and gaslighting me.
2. I'll only work 1 day in a week and accomplish nothing.
3. I'll explore other models / providers to see if I can fill the gap.
The right choice is very clear. But can't Anthropic see that their only moat is that ecosystem was built around claude code because they were first to do this subscription stuff and their harness didn't get in the way too much?
Anthropic tried to fix this I think. Because it's the only model that will push back, but it's even funnier.
Ask a question, it will say yes, ask "are you sure?", it will reverse direction full throttle, then ask are you sure again and it'll go back to initial response saying "yeah I confused myself there". You can do this until context window exhaustion and this will never stop.
On the other side of this, Gemini will stand by whatever it generated the first time, no matter how much you push back and no matter how stupid the idea is.
The limits and response times are laughable. Remove branding and you'd think it's served by some hobbyist on a homelab server, not Google
reply