Offshore
Photo
Evan
🇺🇸 JUDGE RULES GOOGLE $GOOGL NOT REQUIRED TO END PAYMENTS TO APPLE $AAPL AND OTHER PARTNERS FOR PRELOADING GOOGLE PRODUCTS - Reuters https://t.co/j9oDfYY4eo
tweet
🇺🇸 JUDGE RULES GOOGLE $GOOGL NOT REQUIRED TO END PAYMENTS TO APPLE $AAPL AND OTHER PARTNERS FOR PRELOADING GOOGLE PRODUCTS - Reuters https://t.co/j9oDfYY4eo
tweet
Offshore
Photo
soken
"this fat guy want to replace you after tweets said you were died" https://t.co/7JRnc2QgyF
tweet
"this fat guy want to replace you after tweets said you were died" https://t.co/7JRnc2QgyF
tweet
Offshore
Photo
App Economy Insights
Google will NOT be forced to sell Chrome.
No breakup needed, removing a major overhang on $GOOG.
However, Judge Mehta is barring the exclusive search deals like the $20B+ paid to Apple annually in traffic acquisition costs (TAC). https://t.co/vETKDdxGxt
tweet
Google will NOT be forced to sell Chrome.
No breakup needed, removing a major overhang on $GOOG.
However, Judge Mehta is barring the exclusive search deals like the $20B+ paid to Apple annually in traffic acquisition costs (TAC). https://t.co/vETKDdxGxt
tweet
Offshore
Video
Koldo Huici
Sublime coincidences ✨
I never get tired of enjoying Kling 2.1 start–end frame. https://t.co/aSaouk56kP
tweet
Sublime coincidences ✨
I never get tired of enjoying Kling 2.1 start–end frame. https://t.co/aSaouk56kP
tweet
Offshore
Video
The Startup Ideas Podcast (SIP) 🧃
RT @gregisenberg: lee from cursor JUST showed me the future of coding in this 29 min tutorial.
what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break.
imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description.
imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities.
imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included.
lee walked me through how all of this already exists inside cursor.
he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality.
and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically.
you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing.
another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic.
he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean.
pro tip, thanks @leerob.
this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor.
anything is possible.
tweet
RT @gregisenberg: lee from cursor JUST showed me the future of coding in this 29 min tutorial.
what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break.
imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description.
imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities.
imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included.
lee walked me through how all of this already exists inside cursor.
he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality.
and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically.
you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing.
another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic.
he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean.
pro tip, thanks @leerob.
this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor.
anything is possible.
tweet
Offshore
Photo
Riley Brown
Of all the CLI tools Gemini CLI has the best interface...
Gemini CLI was just added @sandboxvibe.
And for 30 more hours is free to try.
Currently i'm building a angry birds with
- Claude Code
- Gemini CLI
- Codex with GPT-5 High
All at the same time, in the web.
Video later.
tweet
Of all the CLI tools Gemini CLI has the best interface...
Gemini CLI was just added @sandboxvibe.
And for 30 more hours is free to try.
Currently i'm building a angry birds with
- Claude Code
- Gemini CLI
- Codex with GPT-5 High
All at the same time, in the web.
Video later.
tweet
Offshore
Video
The Startup Ideas Podcast (SIP) 🧃
“GPT-5 is so whack... Claude Code RuInED my ProJect”
No. You ruined your project.
Here’s how to fix your vibe code project:
STOP adding context.
You’re cramming a mansion into a studio apartment and wondering why nothing fits.
- At 80% context window, the model starts hallucinating.
- At 90%, it’s completely lost.
-At 100%, you’re coding blind.
You’re not using AI wrong.
You’re overloading it.
The Fresh Start Protocol:
1) One feature = One new chat
2) Keep context under 50% capacity
3) Only include files directly needed
4) Start fresh when quality drops
5) Never auto-summarize (it loses critical details)
Stop treating AI like infinite memory.
Start treating it like a focused assistant.
New feature.
New chat.
Clean context.
That’s how you graduate from vibe coding slop to shipping production apps.
The models aren’t getting worse.
Your context management needs to be better.
tweet
“GPT-5 is so whack... Claude Code RuInED my ProJect”
No. You ruined your project.
Here’s how to fix your vibe code project:
STOP adding context.
You’re cramming a mansion into a studio apartment and wondering why nothing fits.
- At 80% context window, the model starts hallucinating.
- At 90%, it’s completely lost.
-At 100%, you’re coding blind.
You’re not using AI wrong.
You’re overloading it.
The Fresh Start Protocol:
1) One feature = One new chat
2) Keep context under 50% capacity
3) Only include files directly needed
4) Start fresh when quality drops
5) Never auto-summarize (it loses critical details)
Stop treating AI like infinite memory.
Start treating it like a focused assistant.
New feature.
New chat.
Clean context.
That’s how you graduate from vibe coding slop to shipping production apps.
The models aren’t getting worse.
Your context management needs to be better.
tweet