How can we reimagine software development with AI to not just improve developer productivity but also to ensure software safety, reliability, and maintainability while keeping it personalized to developer preferences?
Read more about our latest project, PwR (pronounced Power)
PwR uses domain-specific languages to bridge communication between developers and AI tools. Learn how it can help simplify code creation and enhance software reliability and customization, no matter your coding expertise: https://t.co/KREB760uB1
🏃♂️ I've gamified my own run so I can race my own ghost with the Meta Ray-Ban Display.
I built a web app for the glasses, loaded a previous GPX from Strava, and dropped game mechanics on top.
Pick up coins when you keep pace, sprint zones reward extra points if you push, and a mini leaderboard on the lens shows how you're tracking against your past self in real time.
Best part: it actually works. Seeing your ghost 20 m ahead is a way stronger nudge than any number on a watch. 😅
THE FIRST MAN IN HISTORY TO BREAK 2 HOURS IN A MARATHON!!!🤯🤯🤯
Sabastian Sawe 🇰🇪 has just shattered the World Record at the London Marathon, running 1:59:30!!!
He makes history as the first man to officially break 2 hours in the marathon.
Yomif Kejelcha 🇪🇹 in his debut ran 1:59:41 to become 2nd fastest alltime, while Jacob Kiplimo 🇺🇬 finished in 2:00:28.
All under the previous World Record.
@deedydas I got it to design our future house. It generated the floor plan and then did isometric views to better visualise it. There are subtle errors but as a non-architect, I am thrilled to see what our dream could look like.
Saying not knowing how to code gives you an advantage in building software (thanks to AI) is like saying not knowing anything about filmmaking gives you an advantage in making films (thanks to having a smartphone + apps to edit stuff)
Ignore this stuff and keep learning+building
In the era of algorithmic distraction, the ability to maintain a single thread of thought for four hours is a superpower. It is the only way to solve hard problems.
Software engineering changed more in the last 3 months than the preceeding 30 years.
Everything about running a software company needs to be rethought from first principles.
“Every technical person I know is doing the same math right now. They won’t call it that. They’ll say they’re “exploring options” or “thinking about what’s next.” But underneath it’s the same calculation: how much is it costing me to stay where I am?”
The 100x bar has shattered.
The best developers will maximise number of agent hours per day (24 hrs)!
“We regularly see single Codex runs work on a single task for upwards of six hours (often while the humans are sleeping).” https://t.co/uDEreq0Vkr
When manual programming became obsolete around 2026, it represented almost exactly 183 years¹ of refinement by some of the best minds of our times. That is a really long run, but the runs are getting shorter.
¹ Since Ada Lovelace's "Note G"
https://t.co/Ci58GcGk6L
It’s really important to fight the urge to manually fix code when agents struggle and instead ask the deeper questions:
“what capability is missing, and how do we make it both legible and enforceable for the agent?”” https://t.co/uDEreq0Vkr
@PranavKumb77907 Thanks, it was fairly easy to do the setup. ~3 agent hours for the skills and scripts, with minimal supervision:
- analyst: fetch data from Google Sheets and use pandas/python for local analysis
- researcher: access specific credible sources through browser automation
Getting beautifully formatted emails from a coding agent that built two skills (researcher, analyst) and the scripts to run scenario analysis for raising cash. Feels like having a tiny investment team on tap.
Yes, definitely it takes time to setup and keep the agents productive as requirements drift, but it’s always worth it.
I have experienced this sinusoidal wave of productivity across my projects as it progresses. It takes a Herculean task to observe what the agents are doing wrong and get them back on track.
Every time you manually do the work you optimise for the current output (short term win) and compromise the process that could give you N outputs (long term win).
“A local agent makes one developer faster. A cloud agent, once configured and taught your conventions, makes the entire org faster.
Expertise gets encoded once and executed repeatedly.”