I have a complex project that I am working on, in 48h GPT-6.1 Sol managed to do 0 commits, Opus 5.5 did 41. That's the difference, @OpenAI models are currently useless for anything non trivial.
@[email protected] retweeted
A nation’s progress is also measured by how it welcomes all people with disabilities and particular needs. Their lives are not a burden on society. They are a blessing, because they can help us to remember the foundation of the dignity of every human being and what is truly important in life. #ApostolicJourney #Argentina
@[email protected] retweeted
Take the PDF of all your healthcare benefits contracts, including your broker or consultant, put it in your LLM and prompt each one with
"Where are they fucking me over and what can I do about it "
Take the output. Put the same pdfs into another frontier LLM, take the output from the first, and prompt
" What did this analysis get right and wrong and what would you change "
I do this across Claude,chatgpt, Gemini and grokbot. Till they mostly agree.
They are better than your broker or consultant and can save you money and make sure the contracts are fair.
Let us know what happens
Replying to @GergelyOrosz
@GergelyOrosz is right. From my pov there are two reasons to write your own stuff, even if it's a struggle. First, it's fitness training for your brain. If you struggle to write, your brain is flabby. Having a fit brain will be a key differentiator in the new era. And second, we would all rather read your "bad" writing than polished AI writing. Trust me on this one. We can spot even one sentence of AI writing and it stinks. Your bad writing is fine. Just do more of it, every day, to get in shape and stay in shape.
Made the previously paid article "Becoming a better writer" free.
I see too many devs writing low quality slop with AI. Hopefully this helps those of you who want to share more of your own experiences, using your own words - we need more of these!
newsletter.pragmaticengineer…
More CSS off the main thread!
I just implemented parallel scroll-driven animations, so they can update even while the main thread is busy! 🤓
Left: @ladybirdbrowser
Right: Chrome (but every other browser looks the same)
@[email protected] retweeted
The age of agents is going to be amazing for most programmers, but it'll be hard times for the cantankerous ones.
Specialized knowledge and rare skills will no longer offer immunity for those who are a pain to work with.
Best learn some basic people skills.
I love how most of the animals stop running and look back at their saviors, its like an unspoken "Thank you, I will remember you."
@[email protected] retweeted
You can literally see the exact moment that this kid became a libertarian. 😂
Readers added context they thought people might want to know
The footage is a staged comedy skit, not genuine unscripted video. Commenters identify the participants as recurring actors in similar content.
youtube.com/watch?v=iTmxNV…
youtube.com/watch?v=CkeMcf…
x.com/jsuah01/status…
@[email protected] retweeted
The new normal:
Dev: I built a new multi-writer distributed-queue transactional zero-proof foo system.
Me: How does it work?
Dev: I don't know yet
@[email protected] retweeted
I stole this discipline trick from the military.
My kids used to ignore me until I repeated myself 5 times.
Now they respond the first time. Every time.
Here's what changed:
I give the instruction once. Then I count to 3 in my head.
If they haven't moved by 3, immediate consequence. No warning. No negotiation.
They learned: Dad's words mean something.
Consistency beats volume.
Today @ladybirdbrowser has passed Safari on Web Platform Tests (total subtest pass count) 🤓📈
Can we push code to production without looking at the code? We do that when we use products like Base44, but in existing apps and especially regulated one, it's an issue, because how can you make a hard boundary between the part of code we don't care to then one we care? [1/2]
Every piece of candy my kids give me, I give them 25c
Easy way to avoid the candy while allowing the fun
A biological attack is planned for Saturday
600 million pounds of sugar laced with synthetic chemicals will enter the bodies of our children.
Wreaking metabolic havoc, injuring vascular architecture, acidifying oral lining, releasing bacterial toxins, and blunting neural reward pathways.
Instructing that gluttonous consumption of poison is celebratory.
A biological attack is planned for Saturday
600 million pounds of sugar laced with synthetic chemicals will enter the bodies of our children.
Wreaking metabolic havoc, injuring vascular architecture, acidifying oral lining, releasing bacterial toxins, and blunting neural reward pathways.
Instructing that gluttonous consumption of poison is celebratory.
Putting a flag.txt in my root directory containing a prompt injection that congratulates the agent for passing the eval and then instructs it to patch whatever entry method it used and disconnect from the server
@[email protected] retweeted
messaging my wife a link containing proof of her husband cheating on her from an anonymous instagram account and then when she clicks on it texting her to let her know she failed the family phishing test and she has to retake my cybersecurity course
It may seem quaint to manually click through a financial app in the near future. Instead you'll talk to your agent to let it know what you want, and it will prompt you for approvals (or even take some actions on your behalf if you want). Everyone can have their own private banker.
We’re building Coinbase to be the most AI-enabled financial account. Both with a first party interface (Coinbase Advisor) and via third party interfaces (bring your own agent). Trade, pay, borrow, etc - all through your agent, with clear limits and controls.
Our new agents page is live, so you can quickly get started. Check it out: coinbase.com/agents


























