There are lot of readymade neovim configs you can copy. I was experimenting recently with lazy.vim and took a git clone and cp command to get up and running
The problem is that for any non-trivial question agents have to grep A LOT to understand the high-level logic expressed in code. In big projects grepping can take minutes some times. Lat short-circuits grepping significantly with `lat search` that agents happily use.
To be fair an average therapist is also pretty sycophantic. "The worst person you know is being told by their therapist that they did the right thing" is a bit of a meme, but isn't completely false in my experience.
No, the meme is that the average therapist can be boiled down to "well, what do you think?" or "and how does that make you feel?" (of which ELIZA, the original bot that passed the Turing test, was perhaps an unintentional parody). Even this cartoonish characterization demonstrates that the function of therapists is to get you to question yourself so that you can attempt to reframe and re-evaluate your ways of thinking, in a roughly Socratic fashion.
It was entirely intentional. The Rogerian school of psychotherapy stereotyped by “how does that make you feel” was popular at the time and the most popular ELIZA script used that persona to cleverly redirect focus from the bot’s weaknesses in comprehension.
Yeah, I don't think the metaphor applies exactly but I definitely see similarities from my personal experience
1/ Dependency -- Once I got used to agentic coding, I almost always reached out to it even for small changes (e.g. update a yaml config)
2/ Addiction -- In the initial euphoria phase, many people experience not wanting to "waste" any time agent idle and they'd try to assign AI agents task before they go to sleep
3/ You trust your judgement less and less as agent takes over your code
4/ "Slot machine" behavior -- running multiple AI agents parallel on same task in hope of getting some valuable insight from either
5/ Psychosis -- We have all met crypto traders who'd tell you how your 9-5 is stupid and you could be making so much trading NFTs. Social media if full of similar anecodotes these days in regards to vibecoding with people boasting their Claude spend, LOC and what not
In my experience the agent regularly breaks some current features while adding a new one - much more often than a human would. Agents too often forget about the last feature when adding the next and so will break things. Thus I find Agent generated tests important as they stop the agent from making a lot of future mistakes.
It is definitely not foolproof but IMHO, to some extent, it is easier to describe what you expect to see than to implement it so I don't find it unreasonable to think it might provide some advantages in terms of correctness.
In my experience, this tends to be more related to instrumentation / architecture than a lack of ability to describe correct results. TDD is often suggested as a solution.
Given the issues with AWS with Kiro and Github, We already have just a few high-profile examples of what happens when AI is used at scale and even when you let it generate tests which is something you should absolutely not do.
Don't "let it" generate tests. Be intentional. Define them in a way that's slightly oblique to how the production code approaches the problem, so the seams don't match. Heck, that's why it's good to write them before even thinking about the prod side.
I work at aws and generally use Claude Opus 4.6 1M with Kiro (aws’s public competitor to Claude Code). My experience is positive. Kiro writes most of my code. My complaints:
1. Degraded quality over longer context window usage. I have to think about managing context and agents instead of focusing solely on the task.
2. It’s slow (when it’s “thinking”). Especially when it’s tasked with something simple (e.g., I could ask Claude Opus to commit code and submit for review but it’s just faster if I run the commands myself and I don’t want to have to think about conditionally switching to Haiku / faster models mid task execution).
3. It often requires a lot of upfront planning and feedback loop set up to the extent that sometimes I wonder if it would’ve been faster if I did it myself.
A smarter model would be great but there are bigger productivity gains to be had with a good set up, a faster model, and abstracting away the need to think about agents or context usage. I’m still figuring out a good set up. Something with the speed of Haiku with the reasoning of Opus without the overhead of having to think about the management of agents or context would be sweet.
> A smarter model would be great but there are bigger productivity gains to be had with a good set up, a faster model, and abstracting away the need to think about agents or context usage. I’m still figuring out a good set up. Something with the speed of Haiku with the reasoning of Opus without the overhead of having to think about the management of agents or context would be sweet.
I was thinking about this recently. This kind of setup is a Holy Grail everyone is searching for. Make the damn tool produce the right output more of the time. And yet, despite testing the methods provided by the people who claim they get excellent results, I still come to the point where the it gets off rails. Nevertheless, since practically everybody works on resolving this particular issue, and huge amounts of money have been poured into getting it right, I hope in the next year or so we will finally have something we can reliably use.
I know this is being marketed for students and such but honestly even if you are a developer who works primarily with web dev stuff you will be able to do all of it on this device. Or if you are a product manager in a tech company, this is perfect device.
IMO there is a small subset of Mac users today(gamers, local LLM users, editors, mobile devs) for which this won't be the best option
reply