NZ ☄️

Rate your AI dependency out of 10 right now?

@juiceboy_of_abj Yes for frontend. i will stick with codex

@CodeByNZ Gpt 5.6 over opus 4.8?

been busy all day making the best out of gpt 5.6 sol. damn i love this model, worth every dollar.😄 what did you work on today ?

@TimJayas Claude for deep work yes i agree . But gemini, i don’t even use it anymore totally forgot i have the app 😅

@CodeByNZ Claude Fabe for important work and Gemini for quick answers

Which AI model do you actually trust with important work and which one do you just use for quick answers?

@AskSnehasish Yeah, I trust them to help me move faster, not to be right every single time.

@CodeByNZ Apparently, I just don't trust any AI model for the final output until I actually validate it.

@juiceboy_of_abj I like that setup. No point burning your best model on simple questions.

@CodeByNZ I always use opus 4.8 for all my task While fable 5 is available I use it for complex task like payment int, and ask it to review a few logics I use sonnet for quick answers outside my IDE

Any day I skip scrolling on this platform, a thousand and one things happen in the tech niche. WTF do you mean Claude extended Fable 5 access? At this point, they should just keep it.

@proxy_vector Makes sense. If you don’t measure it, it’s hard to know whether the model changed or your expectations did.

@CodeByNZ The giveaway is usually a regression in a specific task, not a vague “feels worse.” Keep a small versioned eval set for your real workflows; otherwise provider updates turn into anecdotes you can’t reproduce.

Which model has gotten worse with updates and you noticed immediately but said nothing?

@deepakThamizhK 😂I feel like a lot of people quietly did the same.

@CodeByNZ claude around early 2025 got noticeably more cautious overnight and i just silently switched workflows lol

@RanHasNotes I haven’t seen Kimi come up as much, but you’re definitely not the first to mention it.

@CodeByNZ Kimi

@AOluwaseun37257 Interesting. I’ve seen a few people mention hallucinations more often lately.

@CodeByNZ Deepseek. Always hallucinating every time

@CCIE_24825 😂

@CodeByNZ github copilot. it has the memory context of a blacked out drunkard.

@0xerik I don’t know about every model, but I’ve definitely had moments where an update felt like a step backward.

@CodeByNZ Literally every single one. Crazy that these companies can just make the models worse and not even tell us about it.

@mretsal It definitely sparked a lot of debate when 4.7 came out.

@CodeByNZ Opus. When they went from 4.6 to 4.7. I immediately knew 4.7 was awful. It was a downgrade.

@jetexpert7 You’re definitely not the only one saying that.

@CodeByNZ Deepseek it has been fucking terrible

@ChaoticBuilder_ Love to hear that. Wishing you a smooth build.

@CodeByNZ I am building now working on PD

Honest question. Are you building with AI or just watching other people build with AI and tweeting about it?

@ashishbdev_ Honestly, that’s the best combo.

@CodeByNZ i am doing both

@DanielGPT2022 As it should be. 🤝

@CodeByNZ Building, man, ofc