Programmer since 1996 turned AI orchestrator | Building @ISNetworld and more | Helping is learning | Dad in Texas | No politics

Texas, USA
Joined February 2021
AI will never accidentally drop a gum wrapper on the sidewalk, watch the wind carry it down the sidewalk a little ways, and then try to chase it down like an ostrich in clown shoes.
15
Seth Livingston retweeted
ever since i was a kid i wanted to hop on a quick call
138
1,757
126
23,776
728,622
Seth Livingston retweeted
I suffer from a rare condition where I keep thinking people will change their minds when presented with facts.
1,108
5,750
405
45,897
553,227
Seth Livingston retweeted
Your future doctor is using ChatGPT to get through exams right now, so please start eating better and exercising.
102
2,080
110
13,429
253,233
Seth Livingston retweeted
Elm 0.19.3 is out today! ✨ elm-lang.org/news/another-st… ✨ Explains the rough roadmap for the next few releases. We are preparing for some exciting improvements and features! 😊
14
87
15
430
17,831
What an absolute gem this is. explainshell.com
26
Ok wait this is NOT AI??
Hey @grok what the hell is this...
40
Seth Livingston retweeted
evergreen advice: keep that angry multi-paragraph post/slack/email in drafts for 72 hours
35
14
9
519
90,327
Seth Livingston retweeted
OMG if this robot says load-bearing one more time i swear I am going to strangle it
15
3
6
172
25,704
Seth Livingston retweeted
companies building their own agent rather than exposing an mcp / cli for their uses is like if you had to download a separate browser for every website you use
86
66
17
1,089
53,828
sonnet has been a reliable workhorse for me at my day job. yesterday it fell flat on its face. wondering if that means things are moving around behind the curtain to fix opus
27
X today: creepy ass robots, haphazard rankings, and plenty of "90% of the people I talk to say that...."
23
Seth Livingston retweeted
i really don't want to use your agent, i want to use my agent to use your thing.
258
419
233
4,566
708,399
Seth Livingston retweeted
AI;DR (AI; didn’t read)
96
2,453
88
18,154
438,003
Seth Livingston retweeted
I think the best admin ui is an mcp server
2
1
3
152
Seth Livingston retweeted
Every idea you shelved as "too ambitious" is now back in play
237
358
85
4,245
168,009
Yep. They’re called government contractors.
You do realize that out there, right now, there are enterprises with thousands of developers and they are all WRITING CODE BY HAND. Because no AI access is allowed or budgeted. In fact, I'm going to guess that this is likely the norm. And that blows my mind.
29
I’ll believe this when I see it. And I doubt it.
You can now set Claude Code's output style to Concise. Claude leads with the result, keeps responses short, and still gives full detail when you ask. Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
1
75
it’s my understanding that kids are now calling the 80’s and 90’s the late 1900’s i’m angry
21
we've really gone too far. i think about this a lot. partially out of respect for the Lorax, but more so because it's just an egregious waste of power and resources. it's hard to swallow as an engineer.
Something I routinely am in awe about is the compute amplification every commit has today vs. 20 years ago, at least personally. Back then, my personal computer was only non-idle when I was working locally. I ran tests locally. When I pushed, there was no CI. The tests themselves were minimal maturity (simple unit tests, some e2e). Today when I push, CI exists. It fans out to 200+ jobs across macOS, Linux, and Windows that take ~20 minutes to complete in totality. A successful CI triggers ~8 beefy machines for tip releases. Tip releases trigger Apple notarization machines. Simultaneously, I have dedicated machines running 24/7 doing fuzz testing at basically 100% CPU constantly. Locally, my computer is using CPU much more of the day due to background agents. My average CPU utilization on my M4 Max overnight the last 7 days was over 20%. "Low" but before my average would've been 0% (deep sleep)! Plus, those agents are commanding a ton of GPU utilization elsewhere. I'm not making any judgement here of whether this is good or bad, because I think there are both good elements and bad elements. Simply that its quite astonishing how much compute my daily work amplifies in 2026 vs. 2006.
2
2
45