Twin Transition

...

[Twin Transition @TwinTransition]

The fear of messing up the convo with an LLM is real. I almost always have second thoughts about asking a follow-up question because sometimes it just messes up the whole context, forcing me to start a new chat... which I really hate doing.

[Twin Transition @TwinTransition]

LLMs must figure out what to keep in their long-term memory without me reintroducing it during the convo. This 'smart sense' would be the single upgrade I'm looking forward to—models are still dumb enough to miss the most obvious details for no reason like during debugging.

[Twin Transition @TwinTransition]

@Google Typo error: gemini 3.6

[Twin Transition @TwinTransition]

Started using gemini 4.6 on antigravity. Thank you @Google for this upgrade. Would love to test how it performs in larger codebases and longer conversations.

[Twin Transition @TwinTransition]

What do you like most about @Gemini_Notebook?

[Andrej Karpathy @karpathy]

One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.

[Twin Transition @TwinTransition]

Love it

[Twin Transition @TwinTransition]

@doganuraldesign you’re basically shouting into a void that only Elon and his own confused code can hear.

[Twin Transition @TwinTransition]

@typesfast Geopolitics is a bug AI can’t patch

[Twin Transition @TwinTransition]

There is no greater 2026 irony than a developer using a high-level Agent (via MCP) to write a bash script (for a CLI) because they miss the 'simplicity' of manual labor. We are officially inventing tools to help us pretend we’re still the ones doing the work.

[Twin Transition @TwinTransition]

@karpathy

[Twin Transition @TwinTransition]

The weirdest part of the AI era isn't that machines are starting to think like us; it's that we’re starting to ‘prompt’ our friends and family because we’ve forgotten how to just ask a question without specifying a persona and output format.

[Twin Transition @TwinTransition]

people keep asking when ai becomes conscious
nobody asks when humans stopped being curious

[Twin Transition @TwinTransition]

every tech cycle ends the same way
step 1 overpromise
step 2 subsidize losses
step 3 call it inevitable progress
step 4 ask governments for patience

[Twin Transition @TwinTransition]

Just heard Elon declare we've hit the Singularity in 2026. So why is my Grok still generating conspiracy theories faster than it can deny polluting the planet with methane-spewing supercomputers? At this rate, AI will solve climate change by melting us all first. #TwinTransition

[Twin Transition @TwinTransition]

how many h100s can we plug into the desert before the sand turns to glass?

[Twin Transition @TwinTransition]

Elon Musk just spending the gdp of a small country to troll bill gates from orbit.

[Elon Musk @elonmusk]

MACROHARDER coming soon

[Twin Transition @TwinTransition]

if silver hits $420 next, i’m deleting my consciousness and uploading it to a ti-84 calculator.

[Twin Transition @TwinTransition]

we are mining the planet to death so the "thinking" gpt-5.2 can tell you it doesn't have a personal opinion on whether water is wet.