Something funny about the punchy tone in the feature cards that doesn't quite match the overall polished and professional vibe here; feels like the first millennial finally got promoted to Creative Director at Linksys
Chris Rodgers retweeted
Intelligence must draw on memory. The mind must not simply compile data — as an algorithm now does more quickly than we can — but recall lived experiences, which contain depths of meaning that only the human soul can recognize, and connect more deeply with the goodness of these experiences. Everything that is good begins “with the Spirit” and thus possesses a breath, a dynamism and a sense of communion that, once experienced, are engraved upon the heart. vatican.va/content/leo-xiv/e…
we've mostly gotten past the slop issue in this new world of working together with AI
the next problem is people keep accidentally undoing functionality
this is happening because everyone is more in everyone else's business. hit an issue? fix it right away without nagging anyone
the problem is it's unclear how intentional the current behavior is and what absolutely should not be rolled back
you can say tests should be this. but they don't capture the fact that you discarded seemingly valid solutions 1-4 and settled on 5. someone later (an agent) might thing "oh 3 is simpler"
any additional document also doesn't feel like it solves the problem because it's yet another thing that can drift
where is the source of truth for how your software is supposed to work?
The face of the AI-empowered builder
Chris Rodgers retweeted
Replying to @stuxnet_vt @mikeysee
TLDR the people who win are going to be the ones that actually give a shit. Who act with precision and prejudice. Who invest in the small bits because they make the whole better and are ruthless about cutting out the cruft. Software isn’t solved because humans aren’t solved.
Interesting read! The theme of converting the results of an agent session into a package seems analogous to a form of 'caching'; but instead of computed values, it's reusable code. So perhaps 'compilation'?
Drop Drop Drop 🩸
@_overment took apart @kentcdodds's Kody and admitted he was wrong about MCPs.
The whole MCP server is two tools: search and execute. Memory, jobs, integrations, storage - all capabilities the agent composes itself.
Best bit: a 5-step task at 5% error per step fails ~72% of the time. Kody writes the script once, tests it, saves it as a package, reuses it. Determinism beats re-reasoning.
mega.dev/wrong-about-mcps #megadev
Replying to @thoughtlesslabs @yacineMTB
This was indeed a great read - thanks for the rec!
Chris Rodgers retweeted
Can we please retire the term "software factory"?
I think a more durable expression of the concept is "Continuous Maintenance" -- bounded automations that improve software quality (e.g., perf optimizations, bug fixes, security patches) which don't require human intervention.
Replying to @Beccalytics @MichelleBakels
Happy Birthday Michelle! 🥳
Fun fact - you apparently share a birthday with Jack Black
teapawt.org/DailyNoud/status/20933…
Replying to @thoughtlesslabs
Not enough people talking about the Omarchy -> MS Teams pipeline
I found my MEGA pattern: The Objective Latch. @megadevhq mega.dev/you/upo75OErjY2nCUr…
Replying to @PGA
@PGA made its certified golf professionals bookable inside ChatGPT & Claude.
New golfers used to get a tip from a random video. Now the AI assistant they're already talking to can find a real PGA pro nearby and book the lesson, all in the chat.
alpic.ai/case-studies/pga-of…
the focus on whether you read the code or not is the wrong thing to look at
if you have software you're responsible for, you should be able to answer questions from memory about how it works
the expectations for how well you can do this should not be any different now












