Unfortunately at my company leads have no insight into employees claude code caps, and no one has ever complained until now. Apparently some people were basically running with insane caps on CC (25k+), if you asked for it you were approved. Which lead to some people doing insane things on CC for no purpose.
Yeah i was looking there earlier, its just we thankfully mostly have macbooks, but i recently found out new devs are getting the smaller 8gb ram macbooks as well. Which is going to be even more frusturating.
Since my team is mostly remote running LLM on a cluster in the office is not really viable short term.
Given our field we cannot really use anything not approved by management. Pretty much if it doesn't leave our machine we can use its just i don't find anything good. We even have some new devs on the macbook neos, and i can't even find anything for them.
I was considering having something run locally within out building but the time when something like that would be avaliable is not near term so i am trying to make the best of what i can do.
Fundamentally one of my biggest gripes with tools like this is that often you are not working with a single repo in anything beyond simple apps.
When I am working with Claude I am often doing it from the root directory of a workspace of dozens of repos. I work with Claude to come up with a plan for implementing a feature and it investigates and plans.That plan often encompasses multiple repositories. Claude then turns large scale plans into smaller issues, or tickets as artifacts.
Imo I found opus 4.6 to be a pretty big step back. Our usage has skyrocketed since 4.6 has come out and the workload has not really changed.
However I can honestly say anthropic is pretty terrible about support, to even billing. My org has a large enterprise contract with anthropic and we have been hitting endless rate limits across the entire org. They have never once responded to our issues, or we get the same generic AI response.
So odds of them addressing issues or responding to people feels low.
The company I work for has a pretty bad bounty system (basically a security@corp email). We have a demo system and a public API with docs. We get around 100 or more emails a day now. Most of it is slop, scams, or my new favourite AI security companies sending us an AI generated pentest un prompted filled with false positives, untrue things, etc. It has become completely useless so no one looks at it.
I had a sales rep even call me up basically trying to book a 3 hour session to review the AI findings unprompted. When I looked at the nearly 250 page report, and saw a critical IIS bug for Windows server (doesn't exist) existing at a scanned IP address of 5xx.x.x.x (yes an impossible IP) publically available in AWS (we exclusively use gcp) I said some very choice words.
Yup. The way he works is all tasks he is issued in a sprint he just fires them through opus in parallel hoping to get a hit on Claude magically solving the ticket having them constantly be iterated on them. He doesnt even try using proper having plans be created.
Often time tickets get fleshed out or requirements change. He just throws everything out and reshoves it into Claude.
I have a coworker who is basically doing this right now he leads our team and is second place overall. Regularly runs opus in parallel he alone is burning through 1k worth of credits a day.
Frankly Claude code is painfully slow. To the point I get frustrated.
On large codebases I often find it taking 20+ minutes to do basic things like writing tests.
Way too often people are like it takes 2 minutes for it to do a full pr. Yeah how big is the code base actually.
I also have a coworker who is about 10x more then everyone else. Burning through credits yet he is one of the lowest performers.{closing in on around 1k worth of credits a day now).
As someone who works at a company who has to manage millions of SSL certificates for IoT devices in extremely terrible network situations I dread this.
One of the biggest issues is handling renewals at scale, and I hate it. Another increasingly frusturation is challenges via DNS are not quick.
It baffles me that parents have become so lazy they don't even want to monitor what their kid does anymore online, and instead expect the government to do all the work.
I remember when my daughter wanted to play Roblox with some friends I sure as shit did my best to monitor and lock down that horrible thing. Same with just general internet monitoring. Whenever she wants to play some game or something I research it.
I have sat down with her countless times and yeah she has broken my trust a few times and she looses access to the internet.
I just wanted to make a tool to help developers. Then when the SaaS launched they instead focused on adding $$$ features instead of fixing bugs, and started heavily pushing their SaaS anytime you used the tool.
They ended up switching to a terrible model with a previous release where if you were a business or in anyway making money you now needed to pay for licenses and it was comically expensive.
The reality is I could have forked it but I don't have the time and patience to deal with everything that comes from a massive project.
I contributed heavily to a project during its early days and spent almost 2.5 years helping it grow. For awhile i was one of the most active contributors.
Then there was talk of turning the project into an actual business, and myself and a few of the original contributers were offered extremely poor paying jobs. That no one took. Then they got a CEO, investors and we were basically forced out of the project unless we joined the company.
I distinctly remember being in a call where we were told they would be relicensing it eventually and launching a SaaS. To protect our work from being used by large companies. I laughed and pointed out the irony in that call that you were doing the same thing.
After that they changed their policy such they do not accept outside PR's. It has killed any interest in supporting open source projects outside personal stuff.