Yes, this rings true, it took me over a month to actually get to at least 1x of my usual productivity with Claude Code. There is a ton of setup and ton of things to learn and try to see what works. What to watch out for and how to babysit it so it doesn't go off the rails (quite heavy handed approach works best for me). It's kind of like a shitty, but very fast and very knowledgable junior developer. At this moment it still maybe isn't "worth it" for a lot of devs if productivity (and developer ergonomics) is the only goal, but it is clear to me that this is where the industry is heading and I think every dev will eventually have to get on board. These tools really just started to be somewhat decent this year. I'm 100% sure that in a year or two it will be the default for everyone in a way that you simply won't be able to compete without it at all. It would be like using a shovel instead of an excavator. Remember, right now is the worst it'll ever be.
The idea here is an IDE for Claude Code specifically. is most likely the strongest coding agent right now, but not everyone loves the command line only interface. So I totally get it.
So I tried it for a hot minute a few weeks ago, but uninstalled promptly once it looked like it just cannot handle pasted images very well at all. It would paste it as huge Base64 string right in there and completely lock up the UI on my MacBook Pro M3 Max. Has that been fixed?
I'm really looking for a good IDE (or something better than just a terminal) for Claude Code, but I was left disappointed by Claudia...
An MCP is definitely on the roadmap. My objective is to become the context engine for LLMs so having a MCP is required. However, there will be things from a UX perspective that you'll lose out on if you just use the MCP.
Just a few months ago I couldn't imagine paying more than $20/mo for any kind of subscription, but here I am paying $200/mo for the Max 20 plan!
Similarly amazed as an experienced dev with 20 YoE (and a fellow Slovak, although US based). The other tools, while helpful, were just not "there" and they were often simply more trouble than they were worth producing a lot of useless garbage. Claude Code is clearly on another level, yes it needs A LOT of handholding; my MO is do Plan Mode until I'm 100% sure it understands the reqs and the planned code changes are reasonable, then let it work, and finally code review what it did (after it auto-fixes things like compiler errors, unit test failures and linting issues). It's kind of like a junior engineer that is a little bit daft but very knowledgeable but works super, super fast and doesn't talk back :)
It is definitely the future, what can I say? This is a clear direction where software development is heading.
When I first tried letting Cursor loose on a relatively small code base (1500 lines, 2 files), I had it fix a bug (or more than one) with a clear testcase and a rough description of the problem, and it was a disaster.
The first commit towards the fix was plausible, though still not fully correct, but in the end not only it wasn't able to fix it, each commit was also becoming more and more baroque. I cut it when it wrote almost 100 lines of code to compare version numbers (which already existed in the source). The problem with discussing the plan is that, while debugging, you don't yourself have a full idea of the plan.
I don't call it a total failure because I asked the AI to improve some error messages to help it debug, and I will keep that code. It's pretty good at writing new code, very good at reviewing it, but for me it was completely incapable of performing maintainance.
These tools and LLMs differ in quality, for me Claude Code with Claude 4 was the first tool that worked well enough. I tried Cursor before, it's been a 6+ months ago though, but I wasn't very impressed.
Same for me. Cursor was a mess for me. I don't know why and how it works for other people. Claude code on the other hand was a success from day one and I'm using it happily for months now.
I used Cursor for about 5 months before switching to Claude Code. I was only productive with Cursor when I used it in a very specific way, which was basically me doing by hand what Claude Code does internally. I maintained planning documents, todo lists, used test driven development and linting tools, etc. My .cursorrules file looks like what I imagine the Claude system prompt to be.
Claude Code took the burden of maintaining that off my shoulders.
Also Cursor was/is utterly useless any all non-Anthropic models, which are the default.
This was a problem I regularly had using Copilot w/ GPT4o or Sonnet 3.5/3.7... sometimes I would end up down a rabbit hole and blow multiple days of work, but more typically I'd be out an hour or two and toss everything to start again.
Don't have this w/ Claude Code working over multiple code bases of 10-30k LOC. Part of the reason is the type of guidance I give in the memory files helps keep this at bay, as does linting (ie. class/file length), but I also chunk things up into features that I PR review and have it refactor to keep things super tidy.
Yeah, Github Copilot just didn't work for me at all. The completions are OK and I actually still use it for that but the agent part is completely useless. Claude Code is in another league.
Fwiw, I dipped my toes into AI assisted coding a few weeks ago and started with cursor. Was very unimpressed (spent more time prompting and fight the tool than making forward progress) until I tried Claude code. Happily dropped cursor immediately (cancelled my sub) and am now having a great time using CC productively (just the basic $20/mo plan). Still needs hand-holding but it's a net productivity boost.
May I ask what you are use it for? I have been using it for fun mostly, side projects, learning, experimenting. I would never use it for work codebase, unless, well, the company ordered or at least permitted it. And even then, I'm not really sure I would feel comfortable with the level of liberty CC takes. So I'm curious about others.
Of course you need an explicit permit from the company to use (non-local) AI tools.
Before that was given, I used AI as a fancier search engine, and for coming up with solutions to problems I explained in abstract (without copy-pasting actual code in or out).
California doesn't have a special minimum wage for tipped professions? When I was waiting tables a long time ago I think my pay was $1.95 an hour. It was usually just enough to cover tax on tips (the ones we admitted).
> California doesn't have a special minimum wage for tipped professions?
NO STATE has a "special minimum wage for tipped professionals". MOST STATES allow tips to be *credited* towards wage, but NO STATE allows an employee to be paid less than minimum wage. There's a "special minimum wage THAT EMPLOYERS MUST CONTRIBUTE TOWARDS a tipped professional'S WAGE", but that's a very different thing than "the minimal amount of pay an employee may receive."
The difference is where the money comes from: directly from employer vs directly from customer. But in all cases *the sum of these sources* must equal the minimum wage.
If the employee is not taking home at least minimum wage, then the employer is guilty of wage theft.
If the employer does not make at least $x towards an employee's wage, the employer is guilty of wage theft.
So instead, read the CA's (and AK, MN, MT, NV, OR, WA) rule as "tips may not be credited towards an employee's salary".
You keep posting this over and over as if states with a lower tipped minimum are equivalent to states with the same minimum, regardless of tips.
You're not wrong that, in states with a lower tipped minimum, the tips act as a credit. But you're ignoring what the power imbalance in those situations can do to an employee, and you're ignoring the fact that in states like that, tips paid by customers are effectively subsidizing the employer out of paying minimum wage.
And I don't think that it would be surprising that wage theft is more common in places where the tipped minimum is set lower than the general minimum.
As a customer, I would much rather know that the employer is paying the full fair minimum wage regardless, and any tip I leave will always be on top of that. I don't want to be paying a part of the employee's wage that the employer would otherwise be paying.
I hear you, but your solution sounds defeatist. Like there's nothing that can be done.
> tips paid by customers are effectively subsidizing the employer out of paying minimum wage.
Not effectively, literally. That is what a credit is.
But I'm making sure that the conversation is clear that anyone not making minimum wage is suffering from wage theft. We have to identify the right problem if we want to fix it.
> As a customer, I would much rather know that the employer is paying the full fair minimum wage regardless
I also like this idea. I don't think there should be a wage credit. It is helpful to reducing wage theft. While I would, personally, get rid of credits I don't think I'd get rid of tipping all together. Certainly at least not until there's a better minimum wage rate.
> I don't want to be paying a part of the employee's wage that the employer would otherwise be paying.
You're always doing this. Either your money goes directly to the employee or is going to the employee through the intermediary of the employer. In the case you are not directly paying the employee you're paying the employer.
They should. It's easy to report. Doesn't matter if nothing happens right away, because the more reports that accumulate the higher priority it becomes.
So instead of trying to tell me how fruitless this is and just give up to endless arguments, maybe report wage theft if you know about it. You can do it anonymously. You can do it for people that tell you. It's not a hopeless situation. Hell, lawyers take payment after the case is won, and you know if your wage is being stolen then others are too
It's easy to report, but retaliation is a thing, and is hard -- and expensive -- to prove. Someone subject to wage theft is not the kind of person who can afford that trouble.
And it's not like restaurant owners don't talk among themselves. Getting blackballed isn't great.
Bottom line is that you seem to think that there's zero reason why people are shy about reporting wage theft. And yet so many people don't want to do it. Maybe try a little humility on and accept that maybe there are reasons you don't know about or don't understand. It's very easy to tell people what they should be doing when you don't have to walk in their shoes.
> but retaliation is a thing, and is hard -- and expensive -- to prove.
My understanding is that it is fairly easy to prove. If you suddenly have a change in working conditions it is considered retaliation. See the example here[0]. Doesn't matter if you're in an at will employment state. If you get terminated really close to a reporting, well, you'll probably take home more money than you would have by working. It's up to the employer to prove the termination was rightful and they can't just say "because".
It also is not expensive. At least not more than the theft. Lawyers working on wage theft generally take payment as part of the recovery. You pay out of the winnings, not up front.
Honestly, a big part of the problem is that many people have defeatist attitudes. A lot of people don't even bother to make a report after they leave. It is hard to retaliate when you've left.
> it's not like restaurant owners don't talk among themselves
I’m sympathetic to the arguments, but this sounds like scaremongering.
If you have evidence of it, please post.
There are so many restaurants everywhere, just leave the worst place off your resume. I can’t see owners coordinating if there’s no online platform for it.
Looks like it changed in 1988 due to a state supreme court ruling about a 1975 law. The law said the tips were the "sole property" of the employee and couldn't be counted by the employer as wages.
reply