This. I found superpowers a huge token guzzler. And more generic a skill is the worse it seemed to perform. I have found that skills are something you need to build yourself and for your needs and most importantly be willing to throw away. One team I know blindly checked this into every repo they had. They also had the highest cost per pr across all teams in our org (of about 60 eng teams). AI has already given people superpowers. How sad is it that they now need to be told how to just chat and prompt and use AI effectively as a pair programmer:(
This is what i thought/hoped. But man it is surprisingly buggy. Connections drop so fast and flakily. So many times I steppedd out of the house in a rush hoping remote control would help stay connected. And every time ive been sorely disappointed. Fool me once, fool me ten times....
This is fantastic. Ive been so fortunate to work with the mcp folks last few months on a couple of the SEPs (and my own experimental sdk in go). I used to be a naysayer. "Its just apis" I used to say. "Sheesh the invented another abstraction" I used to say.
What folks dont realize is it is the "P" in MCP that throws people off. When you build a traditional app you have to build forms, ui, req/response handling, bidirectional channels, long running tasks, auth and so on.
With mcp 80% of this common layer is taken care for you. So mcp is really an "app framework" than a protocol (well there is that too).
Unified auth is a huuuge boost. Can't wait to see more cool things!
I've actually been doing this for a year. I call it /checkpoint instead and it does some thing like:
* update our architecture.md and other key md files in folders affected by updates and learnings in this session.
* update claude.md with changes in workflows/tooling/conventions (not project summaries)
* commit
It's been pretty good so far. Nothing fancy. Recently I also asked to keep memories within the repo itself instead of in ~/.claude.
Only downside is it is slow but keeps enough to pass the baton. May be "handoff" would have been a better name!
I am really flabbergasted. How are they thinking using React for a TUI is a flex? Having 5 sessions open - and all idea - is taking up 98% of CPU. Is this another case of - "When all you is hammer, everything looks like nails"?
Im confused. Are you asking how to make money or how to spend your time if money was not a concern?
Answering the second question - I can find 48hours worth of things to do in a 24 hour day and none of them would be about work or just lazying around (nothing wrong with it). Life has so much to offer!!! Yeah AI can produce things. But theres a reason id consume human generated art. And thankfully real deep mastery still takes effort and passion!!
Did they? I can get a 70" "smart"-tv for a few hundred bucks with a crap load of bloatware. But I cannot get the same TV that is "dumb" at anywhere near that price point (I just want a bunch of HDMI ports that I can connect other devices into - including my laptop). Those cost a lot more from what I recall. And part of this was due to TVs being a great port-key to grab your viewing habits etc?
Oh man so many things. I wrote a bunch of cool things a few years ago (and recently too) but have been scared to publish - mainly because even though ive used them in production, I felt publishing means having high quality docs etc. So now the biggest vibe-coding use case is to bring everything I wrote in the past to be
"publish-ready".
A few protoc plugins (I am very much grpc proto first):
protoc-gen-go-wasmjs (https://github.com/panyam/protoc-gen-go-wasmjs) - A protoc plugin for creating wasm bindings out of your grpc services so you can have your "go based backend logic" on the browser:
Plenty more but just dusting off old things has been my biggest thing lately and in the process building tooling to standardize my next gen of apps/sites etc.
There are different degrees of "ai wrote all my code". A very crappy way of doing it is to keep on one shotting it expecting it to "fall on the right solution" - very much infinite monkeys, infinite typewriters scenario.
The other way is to spend a fair bit of time building out a design and ask it to implement it while verifying what it is producing then and there instead of reviewing reams of slop later on. AI still produced 100% - just that it is not as glamorous or as marketing friendly of a sound bite. After all which product manager wants to understand refactoring or TDD or SOLID or design principles etc?
I really don't understand the fetishisizing of the demise of software engineers. Are other knowledge workers like doctors or lawyers going to be exterminated by AI? Or is there even a fantasizing of their demise? The only reason I can think of is shmchaudenfreud (it is relatively barrierless to get into and pays pretty well) and more importantly imo doesn't have cabals like other professions do.
Btw I love using my Claude code to crank out product but I don't get off looking for the day when engineers are a dead breed!
Frankly I really don't know what id don't not in tech. Closest I van think of is some kind of mathematician but don't even know what those "jobs" look like. Academia might be another. But these are all tech adjacent aren't they?
This. Companies are chomping at the bits about developer productivity and how they can do 10x more. What is not clear even if they can fire 90% of their engineers (assuming the 10x productivity gain is real), how are they expecting that even a tiny sliver of that 90% cannot replicate the products - with AI? And if we are in such a world how are those companies' valuations justified any more?
Author here. For those wondering - Claude Code was used but not in the "generate me this huge X with a single shot prompt after 8 hours of thinking" mode :).