I'm burning 50% less weekly Claude Code limits now.
1. Install OpenAI Codex plugin inside Claude Code
2. Then use:
> Claude Fable 5 high for planning
> Codex 5.5 xhigh for execution (using Codex plan, no API)
> Claude Fable 5 max for review
That's it. It works.
One prompt on Fable 5 ran for more than a day, costing more than $1000! Few learnings:
1. /goal + self verification is powerful.
2. Shift from "what to do" -> "what I want"
3. Telling it "what I don't want" works really well
The more big things you work on, the more you realize:
“80% done” is only a third of the way there.
“90% done” is actually halfway there.
Masterpieces are made in the details.
Good shit takes time.
Any speech-to-text APIs that handle multi-lingual input well? When one sentence has words mixed from multiple languages for eg:
What is lohnsteuerbescheinigung? (EN + DE)
Tell me rava pongal recipe (EN + TE)
I tried @elevenlabs@WisprFlow@GeminiApp
Today, we’re releasing a significant upgrade to our specialized reasoning mode, Gemini 3 Deep Think.
Deep Think is built to drive practical applications, enabling researchers to interpret complex data and engineers to model physical systems through code.
With the updated Deep Think, you can turn a sketch into a 3D-printable reality. Deep Think analyzes the drawing, builds the complex shape, and generates a file so you can create the physical object with 3D printing.
This is rolling out now to Google AI Ultra subscribers. Select the "Deep Think" option in the tools menu to get started.
Learn more here: https://t.co/MMGMgDtoK8
One of the best things a country can do for encouraging startups is to take care of the paperwork for them. Registration, taxes etc.
Much cheaper and effective than grants of $ millions.
Just tried this model out of curiosity - entirely different response from the usual politeness of chatgpt, gemini and grok! Definitely worth checking out 💯
🚀 Hello, Kimi K2 Thinking!
The Open-Source Thinking Agent Model is here.
🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%)
🔹 Executes up to 200 – 300 sequential tool calls without human interference
🔹 Excels in reasoning, agentic search, and coding
🔹 256K context window
Built as a thinking agent, K2 Thinking marks our latest efforts in test-time scaling — scaling both thinking tokens and tool-calling turns.
K2 Thinking is now live on https://t.co/YutVbwktG0 in chat mode, with full agentic mode coming soon. It is also accessible via API.
🔌 API is live: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/n7xxaszqzF
🔗 Weights & code: https://t.co/4ukcXB0iP6
I miss Google Domains. I bet a lot of other founders do too.
I’ll never understand why Google sold off Google Domains to Squarespace for $180M last year…
Google didn't need the $180m. And it seems like Google Domains would be a pretty strategic asset to own…