Claude Desktop is one of the buggier applications I've ever used and one of our jokes internally is that it seems like it was very clearly vibe coded.
How Anthropic teams use Claude Code
111–120 of 248 posts
Re: How Anthropic teams use Claude Code
#112A repeated trend is that Claude Code only gets 70-80% of the way, which is fine and something I wish was emphasized more by people pushing agents. This bullet point is funny: > Treat it like a slot machine > Save your state before letting Claude work, let it run for 30 minutes, then either accept the result or start fresh rather than trying to wrestle with corrections. Starting over often has a higher success rate th…
$200 per month will get you roughly 4-5 hours of non-stop single-threaded usage per day. A bigger issue here is that the random process is not a good engineering pattern. It's not repeatable, does not drive coherent architecture, and struggles with complex problems. In my experience, problem size correlates inversely with generated code quality. Engineering is a process of divide-and-conquer and there is a good reaso…
Very nice, going to try this out tomorrow on some tough refactors Claude has been struggling with!
Re: How Anthropic teams use Claude Code
#113A repeated trend is that Claude Code only gets 70-80% of the way, which is fine and something I wish was emphasized more by people pushing agents. This bullet point is funny: > Treat it like a slot machine > Save your state before letting Claude work, let it run for 30 minutes, then either accept the result or start fresh rather than trying to wrestle with corrections. Starting over often has a higher success rate th…
Not to mention, if an employee could usually write pretty good code but maybe 30% of the time they wrote something so non-functional it had to be entirely scrapped, they'd be fired.
But what if he only want 20$/per month?
Re: How Anthropic teams use Claude Code
#114A repeated trend is that Claude Code only gets 70-80% of the way, which is fine and something I wish was emphasized more by people pushing agents. This bullet point is funny: > Treat it like a slot machine > Save your state before letting Claude work, let it run for 30 minutes, then either accept the result or start fresh rather than trying to wrestle with corrections. Starting over often has a higher success rate th…
Who is paying?
Should be the same party as is getting the rewards of the productivity gains.
Re: How Anthropic teams use Claude Code
#115I prefer to use Claude code like a smart rubber ducky while I write most the code in the end. I added rules to make claude first explain what it want to do in chat (and code changes should only be implemented if I ask for it). I like it to talk about ideas, discuss solutions and approaches. But I am in control of it - in the end, I am the person repsonsible for the code.
Since I don't like it to automatically do changes to files, I copy&paste the code from terminal to the IDE. That seems slow at first, but it allows me to correct the bigger and smaller issues on the fly faster than prompting Claude to my preffered solution. In my opinion, this makes more sense since I have more control and it is easier to spot problematic code. When fixing such issues, I point Claude to changes afterwards to add to its context.
For me Claude is like a very (over) confident junior developer. You have to keep an eye on them and if it is faster do it yourself, then just do it and explain them why you did it. (That might be a bad approach for Juniors, but for Claude it works for me)
Btw, can we talk about that this blog post is written by the company that tries to sell the tool? So we should take it with a huge grain of salt... . Like all what these AI companies are telling us, should probably be ignored for 90 % of time. They either want to raise money or or getting bought by some other company in the end ...
Re: How Anthropic teams use Claude Code
#116Earlier quoted context omitted.
The hilarious part I’ve found is that when it runs into the least bit of trouble with a step on one of its plans, it will say it has been “Deferred” and then make up an excuse for why that’s acceptable. It is sometimes acceptable for humans to use judgment and defer work; the machine doesn’t have judgment so it is not acceptable for it to do so.
My favorite is when you ask Claude to implement two requirements and it implements the first, gets confused by the the second, removes the implementation for the first to “focus” on the second, and then finishes by having implemented nothing.
The implementation is now enterprise grade with robust security, :rocketship_emoji:
Re: How Anthropic teams use Claude Code
#117Earlier quoted context omitted.
Have you seen human-written code?
At least when you tell a human the indentation is wrong, they can fix it on the first try. Watched an AI agent last night try to fix indentation by using sed for 20 minutes before I just fixed it myself after cringing.
I mean... this is a deterministic task, can just run it through autoformatter? Why ask AI to do indentation of all things?
Re: How Anthropic teams use Claude Code
#118So this style of articles is the future? Pages of unconnected bullet points that mention the word "Claude" at least 100 times. No real information and nothing to remember.
The future is that articles will generally be read by machine intelligences more often than human ones. You have to optimize for your audience.
Re: How Anthropic teams use Claude Code
#119Claude Code works well for lots of things; for example yesterday I asked it to switch weather APIs backing a weather site and it came very close to one-shotting the whole thing even though the APIs were quite different. I use it at home via the $20/m subscription and am piloting it at work via AWS Bedrock. When used with Bedrock APIs, at the end of every session it shows you the dollar amount spent which is a bit dis…
Meanwhile I ask it to write what I think are trivial functions and it gets them subtly wrong, but obvious in testing. I would be more suspicious if I were you.
Re: How Anthropic teams use Claude Code
#120LLMs need documentation for semantic instructions and testing for formal verification. In the past efficient human teams could forego both of these and rely on tacit understanding. But this does not exist with LLMs so we will continue to see proliferation of elaborate documentation bases and test bases.
It is very interesting to me how the differences in our intelligences is physically manifested in text. It is one argument against hard-takeoff: the bioneuron can encode information in a sweet spot that cannot be targeted by the perceptron, by the so-called neuralese, by any amount of distillation.