IsOz

Engineer by day. Building iOS apps at night.
Sharing the AI tools that make both possible.

[IsOz @isozdev]

@gilgNYC it is OpenAI's time these days!

[IsOz @isozdev]

@nickbaumann_ this is reallly good, though it can access X☺️

[IsOz @isozdev]

@eidzoku is there any confirmed date? Can we expect in Q4?

[IsOz @isozdev]

I can see that codex is very popular these days with the Sol, need some actions by claude side✋

[IsOz @isozdev]

@bridgemindai @bridgebench Sol is more than enough for me for a reasonable pricr compared to Fable

[IsOz @isozdev]

The 5 hour limit is coming back.

i got used to not watching the clock. this just feels like they took that away again.

[Tibo @thsottiaux]

Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it.

This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of weekly usage and (b) users on the Plus plan are relatively casual and new users, but then also just accidentally eat through their whole weeks usage and then are confused, making it not a great experience.

We are for the upcoming months keeping the 5h limit not enabled for Pro $100 and Pro $200 subscriptions.

[IsOz @isozdev]

Apple refreshed the Mac mini and Mac Studio.

Mini starts at $899 with M6. Studio Ultra can take 512GB.

I already keep agents on a VPS all day. A desk box is nicer. The VPS still wins when you close the laptop.

Do you move the agent home, or leave it on the cheap box?

[IsOz @isozdev]

@itsvlady I find myself going back to codex every time...

[IsOz @isozdev]

@HermesWatcher the fav. model changes everyday. we will see :)

[IsOz @isozdev]

the sticky part just stopped being the model.

it's the spec files, the task list, the place your team already lives.

swapping the model is a dropdown. ripping out the workspace is a quarter.

[OpenAI Developers @OpenAIDevs]

GPT-5.6 is now available in @kirodotdev, bringing our latest models into the workflows developers already use in production to plan, build, test, and review software.

[IsOz @isozdev]

tiny habit that saves an afternoon:

after the agent says it's done, ask for the test it actually ran.

not the one it would run.
the one in the log.
if it can't show that, it didn't finish.✔

[IsOz @isozdev]

ok this one made me sit up.

NVIDIA posted a CPU for the part of agents nobody puts in the demo: orchestration, code exec, keeping the GPU fed.

if your agent feels smart but slow… yeah. that's the gap.

[NVIDIA @nvidia]

The first CPU built for agents is going to work at scale.

@SpaceX is deploying NVIDIA Vera to accelerate the orchestration, code execution, and data processing that powers its next generation of agentic AI — keeping GPUs fed and agents acting fast.

From gigawatt AI factories to orbit. One NVIDIA architecture, everywhere.

[IsOz @isozdev]

Grok 4.6 + Cursor has been the most satisfying combination I’ve used lately.

Though with how fast things move, who knows what next week will bring.

[IsOz @isozdev]

Every week I switch the model I use.

Last week's pick already feels old. The new one is sitting there.

I still haven't locked one in😀

[IsOz @isozdev]

I put Hermes on a VPS.

The agents stay up. 24/7. Memory, cron, Telegram. Laptop can close.

First setup that feels like a system, not a chat tab.

[IsOz @isozdev]

@0xfarjana Hi!

[IsOz @isozdev]

@tesla999999999 hiii

[IsOz @isozdev]

@soha_gul9 hi lets connect

[IsOz @isozdev]

@Islaaa_web3 yess