I think the bigger issue is skipping the process through which you learn. Personally I learn the most when I am stuck on something for hours trying to figure it out and I miss all of that when AI gives a solution right away.
You get more done without realising you're learning less.
> You get more done without realising you're learning less
Unfortunately, I think many folks now just don't place any value on learning or knowing things because they can "just ask AI".
That's probably my biggest fear with AI is that people just don't see any value to knowing things anymore. And quite ironically, AI is amazing for learning new things.
No no no this is incorrect and conjecture with ZERO evidence behind it.
People ABSOLUTELY place a ton of value on. Learning new things? You yourself JUST called this out but somehow “many folks” don’t place value on learning new things? What’s many? 20? 50? A million? Ten million?
I can agree with the claim that people don't place value on learning new things. It may be anecdotal, but I know that a large portion of people I have talked to genuinely do not care. It's sad, but true. I see it all the time in person and through social media.
And the closest known galaxy to the Milky Way, Canis Major Dwarf Galaxy, is just 25,000 light-years away - it's almost incomprehensible how vast the universe is!
And so the rebranding continues... "artificial intelligence" in the 1950s was used to differentiate itself from "cybernetics". Then once it became unmarketable due to the AI winters, we saw "machine learning", and all kinds of " recognition". Now that we have "AI" as a term for any classifier, people who meant the more ambitious version moved to "AGI". Seems like "super intelligence" just moves the treadmill up another step. Curious what we would call it next.
I wonder if we would see more engineering teams transitioning away from git to Sapling. We do need a refresh on how we review and ship code.
I'm aware that GH recently released stacked PRs, but it still seems like a long way to go both from usability and reliability perspective compared to what Meta and likely Anthropic have internally.
My 2c is that agents are not at the level where companies can easily just have unconstrained LLM with tools and let it be. Different parts of the workflow can have different models, different tools, different constraints, guardrails, etc.
The entrypoint still has to come from somewhere, and it's much more convenient to be able to explain the security and legal teams how data is handled, what is logged, how you can have control over a scenario where the agent does something unexpected.
Sure, for a personal project that could be enough, but we all know those companies target enterprise customers, and you would be surprised how little adoption there is when it comes to workflow automation due to the lack of controls.
Mainly gRPC for cross-service communication, k8s, and all the workflows on Temporal with the agent logic as activities.
For tracking and adding guardrails across many agents and having caps (e.g. the same agent type can do at most X of this action in 24 hours) I have created https://actera.dev/
This is great write-up and it's great that we can use AI tools to peek behind the curtain of how games like these were made.
Hopefully it gives more people a creative kick and we see a revival of more games inspired by some of those game mechanism and potentially even move away from using the well-known set of engines to build games with.
I also think the context of building software matters quite a bit as well.
In a big corporation where ownership is fragmented and initiatives that are big enough for the mythical man-month problem to become tangible, big part of the problem becomes aligning the different engineering teams around why something should be built now, why team X and not team Y should do it, doing it securely and having enough confidence for a release.
You get more done without realising you're learning less.