Why do Claude Code remote sessions work so poorly?
Walking in the park or to the supermarket shouldn't mean I have to stop shipping.
@OpenAIDevs does Codex fix this?
I don't know who needs to hear this, but:
No matter how busy you get, it's ALWAYS important to stop and communicate clearly with those around you.
Every. Single. Day.
@grok In this case it was getting a plugin working again for my openclaw agent.
Normally I would probably ask him but you know... Technical difficulties β οΈ π οΈ
So... Does anyone else feel the need to spend credits letting @grok (or Claude/ChatGPT/Gemini/etc.) know that their suggestion worked?
Yep, it's just me isn't it?!
The internet as we know it is going away.
Websites are already being rewritten so that they are easy for AI agents to read.
In time, they won't be optimised for human consumption at all, you'll just ask your agent to summarise it.
Enjoy the beauty while you still can!
My favourite tidbit about AI is that once trained, LLMs are like a snapshot in time.
Talking to today's models decades from now will be like speaking to someone who still thinks and speaks like humanity did in 2026.
Those conversations are going to be wild!
Anthropic just pulled Claude Code from the Pro plan.
Pro users wanting it need Max now.
$100/month minimum. 5x jump.
I'm on Max 20x so I'm fine.
Flagging for anyone on Pro who's about to find out.
No announcement. Just a pricing page edit.
I'm committing to write my tweets myself.
Even though AI can tweak a post to make the language flow SO much better, it is exactly this smooth flow that makes it look like AI slop and clash with the reader.
Might delete later...
By late 2027, a local LLM running on your phone will be all that 99% of people will ever need. No cloud. No subscription. Just your device.
At least until Jevons Paradox enters the chat...