Oz Code

Hooked on code.

[Oz Code @OzCode]

@herdrdev 🙌🫡

[Oz Code @OzCode]

@maxedapps I’m 100% sure I saw a post about a rust version of Postgres just the other day on Hacker News…

[Oz Code @OzCode]

@haydenbleasel This was very confusing…

[Oz Code @OzCode]

When a single community note kills an entire AI startup idea 💀

[Oz Code @OzCode]

@theo This obviously depends on how much money they will earn from people paying for Fable 5 API usage after the 7th. If people turn out to be willing to pay more for Fable 5 they will obviously not include it after 7th. They are conducting market check, for business decisions.

[Oz Code @OzCode]

@yunuspaksoy Atamayanlara atarlar

[Oz Code @OzCode]

@robinebers Anthropic vibecoded their shitty refund page: https://t.co/3i2ZotJLgM

[Oz Code @OzCode]

@StoicYield @robinebers Same here. https://t.co/3i2ZotJLgM

[Oz Code @OzCode]

I am mainly after stuff that can help groom my codebase and keeping it up to date etc in ways that add value.

Not looking for a ”do a code review of the changes in main last x hours” type of automation, or ”check my gmail and do a summary” stuff.

[Oz Code @OzCode]

How are devs using Codex Automations/Claude Routines successfully? I have a rather large repo I’m working in solo, and so far the only thing I’ve come up with is that it updates the user facing docs once every 48h… There must be tons of things you can do?

#codex #claudecode

[Oz Code @OzCode]

@mradamjafer I bet! How do you guys use agentic coding for the development process right now? I'm thinking both for developing features obviously, but more curious how you use it for code review and validation? Have you found proper processes that fits your team to ship solid and fast code?

[Oz Code @OzCode]

Use the fuck out of the shit you build.

[Theo - t3.gg @theo]

@samcmkt - Know your features well
- Know the rough edges where things go wrong
- Know what breaks first when things go wrong
- Use the fuck out of it before making your bugs your user's problem

[Oz Code @OzCode]

@theo @samcmkt This is the way. Honestly, if you sit in your app/system constantly WHILE developing with agents then you know where shit will break in relation to the changes the agents just made. Manual verification, together with letting agents review + re-review a couple of times. 🔥

[Oz Code @OzCode]

@DerekNee @thsottiaux I have the exact same experience since last 2-3 days. Just as I was becoming team codex…

[Oz Code @OzCode]

@thsottiaux Codex, get out there and experience life for me. Then come back and tell me what the sun feels like, what flowers smell like etc. Make no mistakes.

[Oz Code @OzCode]

Just as I was starting to feel like Codex was becoming my go to tool and that it was outperforming Claude in 9/10 instances it suddenly became utter and complete garbage. Codex is literally unusable since the last 2-3 days... What's going on?

[Oz Code @OzCode]

@LLMJunky This was what "/goal get me 100/100 react doctor score (current: 66/100).. Let me review the changes once you are done." got me.

I did get 100/100 though!

[Oz Code @OzCode]

@odysseus0z Well, I definitely got a 100/100 score. These LLM's are always cheeky, lazy little bastards when they can be! 😂

He literally ignored EVERY rule to make sure I went from 66/100 to 100/100.

[Oz Code @OzCode]

@mradamjafer Love seeing more teams from Stockholm. Will be very interesting to follow you and the team! Best of luck.

[Oz Code @OzCode]

@bcherny @PrimeLineAI > Scrollback gutted - session history is barely scrollable. I can't review my own conversation. <- I can confirm this one, started happening very recently as in last 24-48 hours or so? Repro basically just by starting a session and see how fast the chat history is gone.