And the cycle goes on, gonna test it out inside of codex.

Are there human benchmarks that we can game instead of actually improving as a human being so can look better 🤔

It's tempting me

finally got the java LSP working for opencode. it makes it so that when ever it edits a file, the ai gets all the errors and warnings inside of the file it touched

A Language Server Protocol (LSP) is a standard way for developer tools (editors, IDEs, terminal agents) to talk to language-specific “servers” that provide smarts like autocomplete, go-to-definition, hover docs, diagnostics, and refactors.


Why it’s cool in a terminal agent:

- You get IDE-grade features (jump to symbol, references, rename, diagnostics) while working purely in the terminal.

- The agent can understand and navigate many languages consistently via the same protocol, instead of bespoke per-language hacks.

- It enables rich, context-aware assistance (e.g., “what does this function do?” → instant definition/docs) tightly integrated with CLI workflows.

https://youtu.be/dcolM6W5Odc


My current AI paradox, use AI and get dumber, don't and get fired cus you're not outputting what's expected of you these days.

I feel like AI is making senior's abilities atrophied and juniors slaughtered. As a junior you have to give yourselve enough time to truly and slowly understand what your doing with your own "words". But it feels like the one thing we don't have right now is time.

It feels like a race we can't catch up to unless we reach it by building an unstable base. It feels like the only thing we can do is move and adapt as fast as possible.

A counter argument is that if everyone is screwed, then no one is truly screwed. If everyone changes the way of doing things, then expecting the systems everyone before us went through to stay the same and screw us isn't the approach. The systems of building will change with us.

At the end of the day the formula of:

average dev ability * hours(effort) spent

Is going to be the determining factor for the baseline of work whether it is now, 10 years ago or 10 years in the future (unless we are considering AI being smarter than all of us, then everything is pointless anyways)

I genuinely believe the difficulty/amount of effort we are going to need to input is gonna stay the same

Eg: AI can build a frontend easily -> we can now make website extremely individualized for everyone instead of a general one -> back to same(or more) complexity level. Dumb example but you follow the easier makes it harder rule

- TBH, I don't know what the future will bring. I don't know whether the doomer mentality or the optimistic argument will hold. It is a tough life and we're just struggling through it. But I don't think worrying about the far future we don't know about will help.

Imma think short to medium term for now, which is all in AI and part time no AI coding.

What do y'all think about my nonsense rant.

gpt 5.2, smartest model btw

i don't know how i've been surviving without LSP integration, it saves so much back and forth for dumb issues

Currently what it feels like

Didn't know how important it was, this is 100% of my job for the last month.

Creator of opencode

Claude Code gets native LSP support (Score: 150+ in 4 hours)

Link: https://readhacker.news/s/6HXCP
Comments: https://readhacker.news/c/6HXCP

The moment I praise opencode for having built in LSP.

It's funny how sometimes it can make you feel your falling behind in both directions. Like the worst of both worlds.

https://x.com/i/status/2004607146781278521

wait, it works exactly like death note

You send a label to Ryuk’s notebook (example from the README.md: label=something), and at the end of a Testcontainers test suite, when containers/networks/volumes/images are not needed anymore, Ryuk removes all these resources carrying the labels written in its notebook (the Death Note).