19
points
peab
Joined 400 karma
- peabLol I worked at a startup where the CTO did this. The problem was that it was pure spaghetti code. It was so bad it kept me up at night, thinking about how to fix things. I left within 30 days
- Definitely seeing a bit of this, but it isn't constrained to junior devs. It's also pretty solvable by explaining to the person why it's not great, and just updating team norms.
- Same. I love the tesla model y, but it's not perfect. The screen UI is pretty good for the most part, enough that I don't think about carplay too often.
But I do tend to stream audio from my phone more than from the tesla UI, and so I do miss carplay when I think about it.
- It really depends on what kind of code. I've found it incredible for frontend dev, and for scripts. It falls apart in more complex projects and monorepos
- Except in the past, I'd perhaps have to hire a junior engineer to do that 80%. Now i don't need to do that
- If you're only working on one problem that's very valuable to solve, then taking the time to train a classifier is great.
The beauty of LLMs is that you can run a ton of experiments, notebooks, demos etc because you can write classifiers and structure unstructured data so fast, in a reasonably accurate way (at the moment it seems roughly in line with say hiring an intern to label things)
- I think you kinda proved my point. It's a feature that doesn't solve any problems, it's a feature for the sake of being a cool talking point
- I think either you haven't used LLMs for coding in a while, or you're working on things where they might still be limited on.
I've been able to use LLMs to build things in a weekend that I would not have been able to do in the past, without putting in months of serious effort.
I recently rewrote from scratch in a weekend a project that i had made a couple years ago. In a single weekend i now have a better product than I did at the time, when I spent maybe 20x the amount of time on it.
- You actually probably don't need reasoning, as the old non reasoning models like 4o can do this too.
In the past, the agent type flows would work better if you prompted the LLM to write down a plan, or reasoning steps on how to accomplish the task with the available tools. These days, the new models are trained to do this without promoting
- Are there any examples of implementations of this that actually work, and/or are useful? I've seen people write about this, but I haven't seen it anywhere
- I think the term sub-agent is almost entirely useless. An agent is an LLM loop that has reasoning and access to tools.
A "sub agent" is just a tool. It's implantation should be abstracted away from the main agent loop. Whether the tool call is deterministic, has human input, etc, is meaningless outside of the main tool contract (i.e Params in Params out, SLA, etc)
- it's really getting old
- the entire git page is also clearly generated by Claude or ChatGPT. The headers and the emojis in tables give it away.
- I think because so many blogs, resources, textbooks etc focus on scale, developers are biased into thinking that they need to build for scale.
Which is wrong a lot of the time! You need to build what is needed. If only 10 people use your project, the design will be entirely different than if 10 million people use it
- what topics did you make contributions to? From what I understand, it's mostly political and/or controversial topics that have this issue.
- Yeah, but it's the same reason why Cursor forked VS-Code instead of being an extension
- agreed. they'll make the most sense in dense cities like NYC where having a car is more inconvenient because you have to worry about parking.
- I use it maybe once a week or every other week. It's maybe 10$ more than if I'd go pick it up myself, which isn't worth it if I'm ordering a burrito, but if I order for me and my fiance, then I'm usually getting like 50$ worth of food, and the convenience is absolutely worth it.
Also, given my salary, if I'm working late, it's absolutely worth it to order doordash if I'm tired. I wouldn't do it every day because it's harder to eat healthy and only a subset of food doesn't degrade in quality when delivered.
- There's more money to be made right now in selling courses than actually using the LLM well. So these guys pretend that they found all these ways to make agents, and they market it and people buy the course