Lifelong learner and learning facilitator. Dead mall wanderer. Perpetual digresser. 2 Corinthians 13:13

South Florida
Joined May 2018
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
22
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…
823
6,286
975
46,101
2,982,903
Chris Rodgers retweeted
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?
200
35
29
1,189
98,612
The face of the AI-empowered builder
Salesforce charges us $18,000 a month. So I built a replacement. It started as a personal project: one day in Claude Code on the UI. The code quality was poor, so Orchestrator cleaned it up for four days. $5,600 in tokens. It's live. Guess which one we're keeping.
1
14
Chris Rodgers retweeted
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.
1
1
14
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
1
28
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.
1
3
3
115
Chris Rodgers retweeted
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…
3
1
7
244
Chris Rodgers retweeted
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
126
202
36
3,063
106,013
Chris Rodgers retweeted
15 years ago, as a rabid atheist, I met a Greek Orthodox Christian at a function and we started to talk about religion (I have never met this person again). I told him that you had to be really stupid to hold any religious belief. I was a rational man, and couldn't come to believe in made up fairy tales. Religion was not falsifiable. It was all untestable claims about the universe with no value. To my surprise, he didn't argue, he didn't seem moved. He stated: "I agree". And upon gazing over my confused face for a second, he continued. "All religions are unfalsifiable, but one: Christianity" He then quoted the letter of St. Paul to the Romans, where St. Paul states that if Jesus didn't rise from the dead, we are worse than fools. And explained that the central claim of Christianity rests on a historical claim, not a metaphysical one. Amidst people over the centuries trying to distill Christianity to a moral set of teachings, a way of life, a philosophy, Christians keep insisting: well sure, you can do all of that. But we gather here because Christ rose from the dead. And if He didn't, we are worse than fools. I replied that I had to concede on his premise: this was a falsifiable claim. But it was also a false claim, obviously so. So we agreed on one more thing: they were all fools! Almost a decade later, I spent a long time - more than a year, looking deeply into the evidence for Christ's resurrection, I was convinced that by far, the hypothesis that best explained the totality of the facts was that The Word became flesh, and after his death by crucifixion, rose from the dead. It wasn't an easy psychological process because so much of my identity rested on being the smart rational guy that was above all the superstitious nonsense. And because it wasn't easy for me, I know it is not easy for most. Even for most of that year in which I looked at the evidence, it still all felt obviously false. The two things that flipped me the most were: 1) My realization that I was in a sense guilty of the circularity that I accused many religious people of: I *knew* a priori that the resurrection was impossible because well, it is impossible. By already assuming this explanation was out, every other was immediately better. But once I opened myself to the possibility that it could be true, however unlikely, it changed things completely for me 2) My realization that I had to look at the totality of evidence instead of expecting that each piece of evidence on its own would explain the whole thing. Funny enough I didn't apply this standard to anything else, but applied to the claim of the resurrection. It was a confusing time for me but I then decided that if that was true, I couldn't just sit idly and had to do something about it. This all happened around 6 years ago. And I am here to tell you that after 2,000 years, this crazy claim survives for a reason: it is true. And if it isn't, I am worse than a fool. Which you likely think I am, like I thought of that unnamed person whom I never met again. I don't talk about it often and as a rule of thumb don't argue about it woth anyone, because as I learned with my own experience going through it, the frame of mind matters. Something has to click (this is true for all big mental shifts, not just this one) Perhaps you are a recent follower of mine, and lost all respect for me now - as I would have done back then. But I pray to the Lord that at least for some of you, I can be the small crack that opens the dam of the truth for you. Know that Jesus Christ, God made flesh, loves you. And he offered himself in sacrifice for you.
170
354
27
3,050
95,912
Chris Rodgers retweeted
Few things are as vapid as the phrase “creating value”.
38
7
2
154
86,426
Chris Rodgers retweeted
The idea of "AI employees" feels so short-sighted to me - both disrespectful to humans and a complete misunderstanding of what these tools can do and how to best put them to work You may as well start adding Excel spreadsheets to your org chart
178
184
54
1,749
126,745
I’m calling it: best swag at AIE (and there was some stiff competition!) Thanks @Beccalytics @Gabo_Mart and @g2i_co for the wicked wears + accessories! 🙏
1
2
6
362
Inspiring thoughts from @theo at the close of @aiDotEngineer - challenging us to think big(ger) and move beyond the skeuomorphic phase of AI software; what will the AI parallel to iOS 7 look like?
27
Great talk by @Gabo_Mart at @aiDotEngineer on how to avoid slop in your codebase. Put simply: Human judgment and accountability are paramount. When they are sacrificed in pursuit of faster/cheap code generation, the maintenance bill comes due in the form of expensive evaluation
1
21
Enjoyed learning about Product Engineering strategies from @kentcdodds at @aiDotEngineer ! Beyond the technical 'how' of implementation details - the skill of discerning _what_ to build and the 'why' behind it is indeed more important than ever
1
2
9
3,275
Stoked to see the great @TejasKumar_ give a deep dive on evals at @aiDotEngineer ! Walked away with a new perspective on their value and the nuances involved (eg, their innate biases). Worked through some examples in real time to solidify the knowledge
1
1
3
700