Isn't it just arguing that one complex weighted graph was tuned to output tokens that more align with what current day users would define as 'taste'?
I don't think it necessarily says anything about a model itself having 'taste' in some subjective way.
If the fashion changes would the model update with it without retraining? No. So the model doesn't have 'taste' in that sense. It has alignment to current human definitions of taste.
Yeah I can kind of see that and if you don't like them you don't like them. Not all tools are for all people.
I personally draw the line at plugins that try to set up entire workflows and take the human completely out of the loop. Those are next to useless imo for an engineer who knows what they are doing and are exactly how you end up with crappy code/products.
But to give my thoughts to your points I guess I just don't really care that I can't teach LLMs? It doesn't bother me because I do also still teach people, it's not one or the other.
On what you like about coding. I like that too, I still do it where I want to or where it is needed.
I agree with you on what parts are enjoyable but I guess I don't feel that I'm giving them up? I get to pick the problems I work on that way now. The only disagreement there is around 'clever' shortcuts. I get pleasure out of making things debuggable and traceable for humans.
I wish my odds at gambling were as high as they are with LLM generated code lol.
I do run into the whole 'this session was a waste, need to restart', but like once in a blue moon? Not nearly enough to turn me off from using LLMs daily.
On the teaching point again, my learnings around coding standards, architecture -> problem mapping, how to debug, are applied at the system prompt level and around a few key skill files, so when I say "implement ..." or "I'm seeing this behavior, where in the codebase is the most likely root cause? Why?" It does so close to how I would've done it.
I cannot speak for people who are using these things raw in the harnesses provided by the companies, or god forbid in the browser but you can definitely increase the odds of a good roll enough to be productive by changing the environment around the llm and to me that is the opposite of feeling helpless when it comes to LLMs.
I feel enabled to get more done, at my standards, on my time.
I was already spending a lot of time reviewing other people's code. It makes no difference to me if it's coming from an agent or a person.
I can pick and choose which parts of the problem deserve my attention and which can be done by the LLM with me just keeping an eye on it while I mostly work on something else. I don't have metrics but I feel like I am doing higher leverage work with less friction.
Setting up the systems around the LLM itself is fun too. Hacking on harnesses and trying to improve the UX or the metrics is fun. Playing with different workflow topologies across agents is fun.
Diving deep into context strategies, memory systems, prompting is fun.
Trying to marry ideas from the past with what LLMs enable now is fun.
I don't see how this is soulless or unbearable but granted I'm not at a place that is demanding I maximize throughput. That would suck.
Same loved them, told my team about them, got them to switch off of cursor, now I'm telling them to swap to Codex.
Anthropic really pissed me off with their harness crap. They're well within their rights but their communication over it was enough to get me to swap. I don't need extra hurdles when there's a perfectly valid alternative right there. They don't have the advantage they think they do.
It can and it does especially combined with skills (context files). It can hit REST APIs with CURL just fine. MCP is basically just another standard.
Where it comes in handy has mostly been in distribution honestly. There's something very "open apis web era" about MCP servers where because every company rushed to publish them, you can write a lot of creative integrations a bit more easily.
Not the guy who made it but I immediately wondered if I could use the intermediate steps with some "outline" mode to help me see things in shapes and finally learn to draw a bit.
I don't agree entirely with this. I know why the LLM wrote the code that way. Because I told it to and _I_ know why I want the code that way.
If people are letting the LLM decide how the code will be written then I think they're using them wrong and yes 100% they won't understand the code as well as if they had written it by hand.
LLMs are just good pattern matchers and can spit out text faster than humans, so that's what I use them for mostly.
Anything that requires actual brainpower and thinking is still my domain. I just type a lot less than I used to.
Like the the other commenter said, just for the permissions.
If Bun had a sandbox I'd use it.
Deno isn't my cup of tea (although I appreciate it more after building with it the past two days). My impression is that it is lightweight, you can deploy it easily to edge workers and it's built on rust so you can actually use it to build your own runtime with only the parts you want. (I was working on this for a game when I ran into the CF blog article).
Node/npm is the grandpa, can't go wrong but it doesn't run typescript by default and you'll lose cool points.
pnpm is cool don't really know what makes it different these days except it has a nice cache by default so you get faster installs, and you can do monorepos semi-easily. It's my default if I can't use Bun.
Bun is newer and my current favorite. You can compile to single executable, have access to most of the npm ecosystem (some packages still have minor issues), you have a built in sqlite db so it's great for prototyping, and some other niceties.
There's a lot more to it but that's the important differences I run into in my day to day.
Yes I'm actually not too fond of the DX of Deno. I don't know why. It's a perfectly fine runtime and the permissions are obviously great but the texture is off if that makes sense.
I always gravitate to Bun when I can, it feels light and fresh.
Also I'm definitely going to try out your project this weekend, I've been looking for something like this to put together a free college info aggregation site from the college's public sites themselves, like financial aid dates, on campus programs, etc..
Haha yes, yes it is. I wrote out and implemented that approach in the links below. I've been playing with it for a few hours and I have to say I actually really really like it.
One thing I ran into is that since the RPC calls are independent Deno processes, you can't keep say DuckDB or SQLite open.
But since it's just typescript on Deno. I can just use a regular server process instead of MCP, expose it through the TS RPC files I define, and the LLM will have access to it.
For those of you interested, I wrote out and built an more RPC typescript centric approach to avoid using other MCP servers at all. Would appreciate some thoughts!
A presentation is a live audio visual medium. If you just want the information as facts with no affect why not read the stats later?