To me history is useful to continue watching or find videos I’ve already seen. Turning it off will remove a feature I actually need. They force us to see their horrible “for you” content in exchange - so shameful.
I'm pretty pragmatic and resist AI hype. However, I am in the camp that the tools we've built do not maximize the potential of the LLMs we have today.
I see 2 things happening in parallel.
1) Tools on existing LLMs continue to improve (cursor -> claude code).
2) The LLMs themselves improve which makes existing tooling better and results in new tooling to take advantage of the improvements.
I'm not sure when I see either of these slowing down and they've been accelerating at a very rapid pace. Perhaps when the funding dries up.
I think that's the question but I believe if we don't have any more LLM improvements that we still have a couple years of tooling improvements using what's there today.
I'm sort of surprised that coding is a leading use case but do not see any reason it would not spread to other industries (what the OP is saying).
> all we want to do is advance the concept of direct cash transfer
I love the simplicity of this. I've been thinking a lot about generosity myself.
And while I don't have $100m, our family also has everything we need. What ideas, resources and tools are there for folks like me who want to be as generous as possible with what we have?
To start, I've set up a Donor Advised Fund because I learned that it's a great way to do something with a bunch of appreciated stock that I don't want to pay taxes on. What other tips do you all have?
Local is often the best way, especially if you don't have resources that would overwhelm them (donating $1 billion to a local food pantry would likely blow it up).
But get involved personally; attend meetings, talk to people in the community, get to know what is being done and by whom, and places where some money goes a long way will start to become clear. In my experience the all-volunteer places are often way underfunded and don't really know what they're doing beyond helping people; if you can help guide them it can be incredibly valuable.
100% do things locally. If there is a food bank in your area, support it heavily. That's the absolute base of the hierarchy of needs. For example, in that blog post, expand the immediate donations. Note $100k to Alameda Food Bank, where my partner Betsy regularly volunteers.
Probably because the alternatives are OpenAI, Google, Meta. Not throwing shade at those companies but it's not hard to win the hearts of developers when that's your competition.
I learned all of my programming outside of university and textbooks. It’s one way to learn. Not the only way though - and it has its limits - but you can get pretty far.
But here is my advice. Learning by doing with AI seems akin to copying source from one location (I.e. view source, stackoverflow).
My tips:
- Understand all of the code in a commit before committing it (per feature/bug).
- Learn by asking AI for other ways or patterns to accomplish the something it suggests.
- Ask Claude Code to explain the code until you understand it.
- If code looks complex, ask if it can be simplified. Then ask why the simple solution is better.
- Tell AI that you’d like to use OOP, functional programming, etc.
One way to measure if you’re learning is to pay attention to how often you accept AI’s first suggestion versus how many times you steer it in a different direction,
It’s really endless if your mindset is to build AND learn. I don’t think you need to worry about it based on the fact you’re here asking this question.
I have found I'm always having to steer it in the right direction. I will think I've given it the right amount of instructions but it tends to do dumb things in ways I haven't anticipated.
Good stuff, and I’d add one more trick from the old Zed Shaw books: if you want to learn something new, type it out yourself. Can you copy paste? Can you make the robot do it? Yes, but going through the motion helps embed it in your brain.
Once it’s deep in your memory, you can take all the shortcuts you want, but now it’s for speed instead of necessity.
Came here to type something similar and saw this comment.
+1
Just repeat this until you understand a language's unique ways of implementing things, and understand why a language has those choices compared to others. I always pick one of these experiments to learn a new language with/out LLM support.
1. Ray tracing
2. Gameboy Emulator
3. Expression evaluation (JSONLogic or Regex)
These are super easy to implement in 100s of lines of code, however if you want to optimize or perfect the implementation, it takes forever and you need to know a language's nuances to get it better. Focus on performance tuning these implementations and see how far you can go.
You can split the second group into two sub-buckets.
Junior devs: who have limited experience or depth in knowledge. They are unable to analyze the output of AI coding agents sufficiently to determine long term viability of the code. I think this is the entirety of who you're speaking of.
Senior devs: who are using it for more than a basic task executor. They have a decade+ of experience and can quickly understand if what the AI coding agent suggests is viable long term or not. When it's not, they understand how to steer it into a more appropriate direction.
reply