One of my favourite videos I've seen in months.

https://youtu.be/mfv0V1SxbNA

i just realized that i am using opencode with wraps codex-cli which wraps gpt-5.1 to build an ai wrapper over mistral ai

it's litterally

ai_wrapper(ai_wrapper(ai_wrapper(ai_wrapper( ))))

i'm cooked and i have a week left for me to live with 40% when i speant 60% of it in one day

guess it's back to dumb models.

Happy that I am working in the greenfield side.

A greenfield project is starting a software system from scratch with no existing code or infrastructure constraints.
A brownfield project is developing new software or features within an existing, operational system, requiring integration with legacy code and infrastructure.


No Vibes Allowed: Solving Hard Problems in Complex Codebases - Dex Horthy, HumanLayer

Apparently when we are in a loop of the ai does something wrong and we yell at it to fix it, and it does something wrong and we yell at it... All an LLM is is a next word predictor looking at the previous words. So it looks at the previous fight and predicts the next thing to be it doing something wrong and you yelling at it. So it gives you the prediction of it doing something wrong.

Damn, I've never thought about it this way.

https://youtu.be/rmvDxxNubIg?t=5m31s

how did i not know that react and react native are coming under the linux foundation????

https://x.com/fb_engineering/status/1975935750509343006

lowkey i really like opensource projects, like people were bugging the opencode team to add oauth for providers like atlassian last week and today it is merged and added to the docs.

btw, the jira and confluence MCP is apparently really cool, you can summerize tickets and search through whole company documents stored in confluence to understand (dig up secrets) about your company and projects.

just asked it if what we've been doing for the past couple of hours is the wrong way to do things and it replied this. I hate AI coding, like not gonna lie. now that i have built the incredibly weak foundations of the project really fast, editing one thing takes so long and is just a pointless spiral. you don't know what is wrong till it blows up in your face at the end.

I need to start using tab complete instead of agents.

https://youtu.be/MNvciiZ5x9A

This is cool

https://youtu.be/UALxgn1MnZo

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.