sukit
sukit on Hacker News
Posted by
sukit on Thursday September 03, 2026 @07:21AM
from the ask-hn dept.
I’ve been following MCP since it first came out.
It got a lot of attention early on, but I haven’t come across many people using it in production.
I may simply have missed them.If you’re using MCP in production, what are you using it for?
What advantages have you found over a normal API or direct tool integration or just CLI?
Been trying to get into jj lately, but I rely a lot on VS Code's git gutter to review changes as I code. Doesn't look like jj has an equivalent in VS Code. Anyone got tool recommendations?
Code can be logically separated, but my mind struggles to do the same. I guess this might require some training?
Using different models to supervise each other sounds reasonable. I’m curious what plans are you subscribed to for Claude and GPT?
I haven’t tried that, does it introduce some kind of “black magic” that makes the agent hard to observe?
Do you manage worktrees manually or leave it to Agent?
Posted by
sukit on Monday March 30, 2026 @08:35AM
from the ask-hn dept.
I’ve been trying to make sense of how people really use tools like Claude Code, especially after seeing some of the workflows shared on Twitter.I started using terminal coding agents around June last year. I used Claude Code for a few months, then switched to Opencode because the experience was rough. My terminal would constantly flicker, formatting was messy, and a single session could drag my...
Fair question. I haven’t done a systematic benchmark yet, so I don’t have hard numbers to point to.
Honestly I’ve mostly been iterating from actual use. The main test has been whether it helps me keep the good parts of brainstorming with the agent, recover context across longer multi PR or multi session work, and reduce friction overall.
So right now the evidence is mostly qualitative and based on my own workflow, not a formal evaluation.
Posted by
sukit on Sunday March 15, 2026 @07:57AM
from the show-hn dept.
Posted by
sukit on Friday January 16, 2026 @07:15AM
from the show-hn dept.
Thanks a lot! I’ll definitely give that a try.
I’ve seen so many people praise Claude Code so highly that my first instinct was to assume I must be using it wrong.
I’ve tried quite a few different workflows and prompting styles — but still haven’t been able to get results anywhere near as good as what those people describe.
That's a great point. I think there is some pattern to when it works well or not, but I’m not sure if that’s universal or just tied to how I use it.
Different prompting styles or workflows might lead to very different outcomes.
I might be misunderstanding how it works, but from what I’ve seen, CLAUDE.md doesn’t seem to be automatically pulled into context.
For example, I’ve explicitly written in CLAUDE.md to avoid using typing.Dict and prefer dict instead — but Claude still occasionally uses typing.Dict.
Do I need to explicitly tell Claude to read CLAUDE.md at the start of every session for it to consistently follow those preferences?
That’s the problem — about 50% of the time, the result is so messy that cleaning it up takes more time than just writing it.
So I wonder is there a better way to prompt or structure things so that I consistently get clean, usable code?
Posted by
sukit on Monday June 23, 2025 @10:08PM
from the ask-hn dept.
I'm trying to figure out the right and effective way to use Claude Code.
So far, my experience hasn't matched what many in the community seem to rave about.Often, it either generates convoluted implementations when simpler ones clearly exist, or it produces code that's riddled with bugs — despite confidently claiming it's correct.
I'm wondering if I'm just not using it properly.Here's my...
Posted by
sukit on Monday June 23, 2025 @05:49AM
from the ask-hn dept.
I'm exploring building a simple agent-based app and came across OpenAI's Agent SDK: https://openai.github.io/openai-agents-js/ . From what I understand, it wraps a lot of functionality — like the agent loop, function calling, and integration with the OpenAI MCP server — which could potentially save me a lot of work compared to using the plain OpenAI SDK.However, I'm wondering:Is the Agent SDK...
Appreciate it, I’ll check it out.
That makes sense — I’ve mostly been using Claude (Sonnet), so I’ll give the GPT-4 series a try and see how it compares. Thanks for the suggestion!
That’s a great idea. I haven’t tried connecting to a browser with something like Playwright before.
Yeah, you’re right — at some point I just have to learn CSS more deeply.
Posted by
sukit on Saturday June 07, 2025 @10:33PM
from the ask-hn dept.
Hi HN,I'm a backend developer who recently started building full-stack apps, mostly using Next.js + shadcn-ui. Given how capable AI coding tools have become lately, I've been relying on them to help me bridge the gap in my frontend skills.For the most part, this has been working great — especially when I can just compose existing shadcn-ui components. I describe the layout and functionality I...
Posted by
sukit on Monday October 31, 2022 @03:04AM
from the self-post dept.
Hi, my company is going to build a web application project using scala. Since Lightbend changed license of akka, should we use akka or play2 anymore? Is there any alternative for play2 framework?