I am a software developer with over 25 years of professional experience and have been working with coding agents for quite some time starting with AutoGPT and now using Claude Code almost 24/7 orchestrated via Task Master to automatically spin up new instances working on a multi layer project.
You are absolutely right. A large portion are influencers (I would estimate around 95% of those you see on YouTube and forums) that are full of hype. I think most are not affiliated with Anthropic or any vendor, they are just trying to sell a course, ebook or some "get rich with AI" scheme.
What I appreciate about Claude Code:
- Since it is a terminal/CLI tool it can be run headlessly from cron jobs or scripts. This makes it easy to automate.
- I appreciate the predictable pricing model. A flat monthly fee gives me access to Claude Sonnet and Opus 4 in five-hour sessions each with its own usage limit that resets at the start of a new session. There is a fair use policy of around 50 sessions per month, but I haven’t hit that yet. I deliberately run only one instance at a time as I prefer to use it responsibly unlike some of the "vibe" influencers who seem to push it to the limit.
That's it. Despite being a CLI based tool, Claude Code is remarkably out of the box for what it offers.
That said, no coding agent I have encountered can fully ingest a large inconsistent legacy codebase especially one with mixed architectures that accumulated over years. This limitation is mainly due to context size constraints, but I expect this to improve as context windows grow.
Thanks. It seems you're right. I started with the first Deluxe Paint myself back then and always incorrectly thought he used it based on the videos I saw.
The same thing happened to me and I'm still sick of it. I lost a lot of emails from the beginning of my career. I found out when I finally got around to backing up my old stuff. There are still a lot of emails that I wish I still had. I know it is / was a free service, but still.
Same here. With prices rising everywhere and a salary of ~40k euros before taxes (which is normal in IT in many EU countries if you don't work for big tech) I hardly have room for another subscription. People here are too quick to say "what is $10 on a $80/hour salary?"
Last year at the beginning of the pandemic I started implementing a devops infrastructure at work where I work as a lead developer. Initially the idea was to allow developers to run anything (or a selection of things) required for production on their local machine (k3s, kind etc) with added tooling for development (consistently working tools inside the container, but even outside by the use of binding). All I needed was a simple way to run containers and the requirements. Docker soon proved to be inadequate, it lacked certain features and I soon moved to k8s for local development and a devops pipeline.
People commit their changes, I (and sometimes another dev) review them and they are pushed to the test environment, from there to staging and then production (with a way to easily roll back). This is all done automatically with out-of-the-box solutions (fluxcd, flagger, kilo, kaniko etc).
At work, Kubernetes is not considered too difficult to manage. Much can be done in a very consistent and complete way unlike Docker. What am I overlooking that makes k8s to be considered snake-oil by so many?
Edit: Forgot to add. I am so happy with k8s that I even run it at home and on my external servers.
I signed up for the copilot technical preview right after it was announced a few months ago, but I haven't gotten an invite yet while all my friends who signed up later did (I feel a bit left out). Is there any way to get an invite sooner? What am I doing wrong?
Then doesn't a patent have to more precisely describe the "scheduler" mechanism or can they leave that out? If so. How can I know that I am not infringing the patent? My entity component system which is > 4 years old already does automatic scheduling with batches (what Unity calls chunks) to optimize the memory layout.
Yes, but their claim is specifically about (quoting my other comment):
> It appears to describe a data-oriented component entity system in which all data types within a component are assigned to chunks (batches) in such a way that they can be optimally grouped with data from components of other entities for optimal memory access.
This is not new either. I and others have done this for years. The term "archetype" is something they made up to describe something that has been done many time before.
Edit: It appears that the term "archetype" was introduced somewhere in the last few years. Not sure then if it is specifically coming from Unity.
It appears to describe a data-oriented component entity system in which all data types within a component are assigned to chunks (batches) in such a way that they can be optimally grouped with data from components of other entities for optimal memory access.
I don't see anything new even when considering the entire context. I have worked on similar data-oriented entity component systems for over 10 years. Unity was actually very late to the game and Sony had to push them to give it more priority.
Edit: Some examples, including the use of chunks, or what I call batches:
You are absolutely right. A large portion are influencers (I would estimate around 95% of those you see on YouTube and forums) that are full of hype. I think most are not affiliated with Anthropic or any vendor, they are just trying to sell a course, ebook or some "get rich with AI" scheme.
What I appreciate about Claude Code:
- Since it is a terminal/CLI tool it can be run headlessly from cron jobs or scripts. This makes it easy to automate.
- I appreciate the predictable pricing model. A flat monthly fee gives me access to Claude Sonnet and Opus 4 in five-hour sessions each with its own usage limit that resets at the start of a new session. There is a fair use policy of around 50 sessions per month, but I haven’t hit that yet. I deliberately run only one instance at a time as I prefer to use it responsibly unlike some of the "vibe" influencers who seem to push it to the limit.
That's it. Despite being a CLI based tool, Claude Code is remarkably out of the box for what it offers.
That said, no coding agent I have encountered can fully ingest a large inconsistent legacy codebase especially one with mixed architectures that accumulated over years. This limitation is mainly due to context size constraints, but I expect this to improve as context windows grow.