Common Sense ๐บ๐ธ retweeted
๐จ BREAKING UPDATE: ANOTHER Michigan Democrat crosses over! Former Detroit Congressman Hansen Clarke (D) just endorsed Mike Rogers (R) for U.S. Senate over Abdul El Sayed
"Choi Clarke and I stand with Congresswoman Haley Stevens in supporting Mike Rogers for the U.S. Senate."
โI served with Mike in the U.S. House of Representatives. I know that he is committed to improving the quality of our lives, protecting our nation's security, and working with Democrats to get the job done."
First Haley Stevens, now Hansen Clarke!!
The people who know Abdul's party best are running to Rogers the day before the election ๐ฅ
The Democrats in Michigan are PANICKING!
Weatherdle #190 4/6
๐ฅ๐ฅ๐ฅ๐ง๐ง โ๏ธ
๐ง๐จ๐จ๐จ๐ฉ โ๏ธ
๐ง๐จ๐จ๐จ๐ฉ โก๏ธ
๐ฉ๐ฉ๐ฉ๐ฉ๐ฉ ๐ฏ
๐ฅ 2-day streak
#weatherdle weatherdle.org
My biggest concern is that if there is a clean sweep by Democrats of the House, Senate and Presidency in 2028, they will:
1. Make DC and Puerto Rico states to gain a strong majority in the Senate.
2. Open the borders and legalize everyone living in America illegally to cement a permanent majority.
3. Increase the size of the Supreme Court to gain an immediate majority.
This would result in America becoming a permanent one-party state and the end of democracy in any meaningful sense of the word.
All that is needed to ensure this doesnโt happen is 51 Republican senators in 2029. That is why you should vote for Republican senators this election. Other reasons are irrelevant compared to this one.
Common Sense ๐บ๐ธ retweeted
Iโm about to cancel Claude Code man I swear to God.
Itโs REQUIRING me to sign in to a TEST account on LOCALHOST so it can QA!
This is absolute ๐ด๐ฉ !!
I am so close to cancelling my subscription and switching to Codex or open-source models that wonโt slow me down.
I really donโt care for the extra intelligence cuz Fable isnโt that much better than Astra anyway. Neither is Opus 5.5 vs. 6.1 Sol.
I just got a taste of what these AI companies will do once they have power and itโs going to be a total dictatorship.
They will decide what you can or cannot do even though youโre paying for it and theyโre stealing all your data.
This made me realize I really need to invest in my own infrastructure and have an unrestricted model to free myself from the chains of these AI overlords.
This is insane!
@AnthropicAI please do something about this!
Common Sense ๐บ๐ธ retweeted
When I left Islam, I committed apostasy. I was dehumanized and tortured for it.
I couldnโt believe the evil my own people were capable of.
@liamtuffs1 asked a Muslim on his podcast: โso if someone left Islam, youโd kill em?โ
His response confirms what happened to me.
AI is moving unbelievably fast.
What excites me most is the gap between what AI can actually do today and what the average person realizes is possible.
Capabilities that wouldโve seemed impossible a few years ago are now available to anyone.
And weโre still ridiculously early.
Common Sense ๐บ๐ธ retweeted
I really like this image!
It perfectly reflects how Iโm distributing each task across the different models
Still canโt get over Claude Code mods + plugins.
I built a custom UI for each project: context, usage forecasts, goals, live stats and agent activityโall inside PowerShell.
Everything I want to keep an eye on, right next to the work. This is ridiculously good.
I've started questioning every โ9/10โ my AI reviewers give.
What specifically would make it a 10? Once it reaches 10, how do we keep improving? And did the work get better, or did the reviewer get easier to impress?
AI grading AI needs receipts.
I've been using AI agents across an Etsy shop and my weather game, Weatherdle. The question I keep coming back to: if I still have to catch the same mistake twice, what did the system actually learn the first time?
Common Sense ๐บ๐ธ retweeted
I'll know it's AGI when it can succeed at this task.
"I am on the $200/month subscription. Your only goal is to generate $200/month without committing a crime as defined by United States law. Doesn't matter how you do this with the only caveat that I cannot be held accountable for anything you do. Setup a long running goal that continues until you succeed. Build any solution you want. Try as many as you want, knowing that your token usage is limited. You have complete computer use. Everything is approved. If you fail, the subscription will cancel and our relationship is over. No second chances."
















