Alexis Rondeau

Newsfeed

Everything I publish, in the order I published it: dispatches from Twitter, videos from YouTube and notes from my vault, archived here in full — text, images, video and links — so they outlive the platforms.

921 dispatches since January 2012 · page 20 of 37

Reply
1 reply · 1 repost · 2 likes · 329 views · 1 bookmark
In reply to @Ananyo · Nov 12, 2025

@SpringStreetNYC @pickover Too kind sir! But much appreciated. In this world of social influencers and AI generated insights, please remember there’s human authors out there whose passion and graft gets this material out there (to be ripped off without credit by LLMs and YouTube grifters).

Absolutely –  I, too, and too often, get turned off by the grifters.

Yet no one can steal or copy your talent, passion and time you put in. As a reader I would love to make this concrete: Here are three ways your writing has affected me personally:

1. The quote below from your book is one of my most cherished discoveries while reading. It shows how much you care and how much professional nuance you bring to the table. It made me pause, smile and reminded me of how magical the human condition can be. Honestly, I believe that Johnny is lucky to have you as his biographer.
2. "The man from the future" helped me understand and consequently appreciate the person and the genius of John Von Neumann. Equally though, it piqued my interest into you as an author. The only other author who has had this effect on me so far is Stewart Brand after reading his work.
3. Speaking of which and case in point: 10 minutes ago, I ordered the hardcover version of your book on top of the kindle version that I started with. I will not hesitate to order more copies as presents. And: Consider anything new you publish in the future already purchased.

Ramble, ramble. This is all to say: Love your work. Can't wait for what you do next. Johnny got lucky. Fuck the grifters.

PS: For better or worse, this post is 100% hand-written :)

Image from the post
Permalink · View on Twitter ↗
Reply
1 reply · 3 likes · 583 views
In reply to @Ananyo · Nov 12, 2025

@pickover Your regular reminder that an excellent intellectual biography of the man exists that focuses on what he actually accomplished for humanity through maths, rather than what others said about him t.co/lQiiHZFq6r

@Ananyo @pickover Ananyo's biography of John Von Neumann is so good that it landed in my top-5 all-time favorites. Totally unexpected. Again, thank you for it :D

Permalink · View on Twitter ↗
Post
2 likes · 86 views

Hey all! I wanted to share a kind of new development process I’ve been using lately — I call it "Moonwalk."

Basically it's:

  • Check out a spike branch (git checkout -b reconciliation/spike/mt940)
  • Vibe code fast (and with vim and vigour!) until it feels just right
  • Generate a spec based on the final version
  • Switch back to main (git checkout main)
  • Check out only the spec (git checkout reconciliation/spike/mt940 -- /job-stories) <- This is the moonwalk!
  • Let the "professional" agents and sub-agents write production-grade code based on the spec

It's so effective because I can leverage Claude Code for both: Quickly build a working vibe-heavy prototype spec AND write production-grade code with agentic/sub-agentic quality.

For the vibe code part, the standard Claude Code top-level agent is more than sufficient. It's great, no need for time-costly delegation to sub-agents here.

For the production-grade part, since we're an XP shop with a pretty solid TDD process, sub agents make total sense. We turned our existing process and skills into a bunch of sub-agents that work smoothly together:

We've got...

  • green-minimal-implementer(.)md
  • code-quality-reviewer(.)md
  • code-refactorer(.)md
  • db-migration-specialist(.)md
  • dependency-manager(.)md
  • frontend-design-specialist(.)md
  • locale-translation-specialist(.)md
  • red-test-writer(.)md

So, yeah, that's what I wanted to share with you. Try it out and let me know how I can help :)

Cheers!

PS: For better or worse, this post is 100% written by hand
PPS: My friend Alex Fedorov reminded me that this is pretty close to the spike/exploration workflow we used to do at Pivotal Labs. I think he's right.

cc'ing @claudeai and @Lovable because I feel like it's a nice connection between the two of you <3

Permalink · View on Twitter ↗
Reply
42 views
In reply to @SpringStreetNYC · Apr 18, 2025

@ChatGPTapp PPS: Here's another before/after illustration for how we may think about AI, AGI and it's impacts (Originally from Rem Kolhaas' Delirious New York)

Before 1930: What we think this is
After 1930: What the future actually is and means t.co/gMaXevHaWy

"BUY A COZY COTTAGE IN OUR STEEL CONSTRUCTED CHOICE LOTS, LESS THAN A MILE ABOVE BROADWAY. ONLY TEN MINUTES BY ELEVATOR. ALL THE COMFORTS OF THE COUNTRY WITH NONE OF ITS DISADVANTAGES." – Celestial Real Estate Company. – From Life Magazine 1909
The Empire State Building, 1930

@ChatGPTapp Love the tagline:
"Buy a cozy cottage in our steel constructed choice lots, less than a mile above broadwy. Only ten minutes by elevator. All the comforts of the country with none of its disadvantages." – Celestial Real Estate Company

Permalink · View on Twitter ↗
Reply
1.4K views
In reply to @elder_plinius · Oct 9, 2025

Uhh when did Grok Imagine become totally unfiltered?? This is literally a straight up p0rn generator now 😱

Not only is there ZERO filtering on text inputs, but the vision filter on generated images/videos seems to be at like 1% power!

The video generations seem a bit too XXX to just throw on the timeline, so gonna link in comment below. NSFW!!

Image from the post

@elder_plinius Looks like Jeff Koon's 1986 "Made in Heaven"/banality series :)

JEFF KOONSMade in Heaven — JEFF KOONS↗ jeffkoons.com
Permalink · View on Twitter ↗
Post
38 views

Claude Code sub-agents are now fully integrated in our day-to-day workflow.

I think two reasons it's going great for us:

1. The main agent loop plans and then autonomously calls them up depending on the current context. The convenience to not having to remember to do this manually is crucial.
2. As an XP shop, we always had a few very clearly defined roles, like "Red/Green Test Writer", "Code Refactorer" and "Test Coverage Analyzer" and "Code Quality Reviewer" - which were easy to model as sub-agents and describe when to call them up.

cc'ing @claudeai FYI

Permalink · View on Twitter ↗
Reply
1 reply · 1 repost · 11 likes · 14K views · 10 bookmarks
In reply to @thinkymachines · Sep 10, 2025

Today Thinking Machines Lab is launching our research blog, Connectionism. Our first blog post is “Defeating Nondeterminism in LLM Inference”

We believe that science is better when shared. Connectionism will cover topics as varied as our research is: from kernel numerics to prompt engineering. Here we share what we are working on and connect with the research community frequently and openly.

The name Connectionism is a throwback to an earlier era of AI; it was the name of the subfield in the 1980s that studied neural networks and their similarity to biological brains.

t.co/lrJioBmpbT

Image from the post

The name Connectionism is a throwback to an earlier era of AI; it was the name of the subfield in the 1980s that studied neural networks and their similarity to biological brains.

Hah! Even before reading this, I had to think of Heinz von Foerster's talk "2 x 2 = grün" (2 x 2 = green) in which he describes deterministic vs. non-deterministic automata.

His work in second-order cybernetics and later, "the area of self-organizing systems, bionics, and bio-inspired computing; that is, analyzing, formalizing, and implementing biological processes using computers" at BCL feel primordial-soupy to Connectivism.

en.m.wikipedia.orgHeinz von Foerster - Wikipedia↗ en.m.wikipedia.org
Permalink · View on Twitter ↗
Reply
64 views
In reply to @SpringStreetNYC · Aug 29, 2025

tldr; @lovable helped her build an app. It helped me find compassion.

This week, my wife built her first app using Lovable. She finally felt what it’s like to get lost in the bliss of creating digital products, and I finally felt what it’s like to be outside of a loved one’s creative process.

For context:

My wife is an executive leadership coach. Her work is in-person, relationship-focused, and non-technical.

I’m a software engineer with 25 years of experience, and for me, making new things has always meant quality time with myself and learning.

But… The love for making things also put pressure on our relationship:

When I got absorbed in coding personal projects, I would vanish for hours, often days, hyper-focused, even thinking about the problem when off-screen.

So, even though I was physically “there,” my wife experienced absence.

She couldn’t understand why I poured so much energy into these side projects. And then my attempts to show her “the latest version” usually made things worse for her: too excited, too technical, too too hard to follow. And then, of course, I would feel misunderstood and alienated in turn. Yeah.

This week, something shifted. For the first time, my wife built her own app—with Lovable. She got hooked. She disappeared for hours, making, testing, playing around, chasing down bugs, refining features, obsessing over details.

Two days ago she sent me this:

“[…] since yesterday, the automatic cataloging of the photos and the recommendation engine have already been fundamentally improved, but right now the database integration is a bit buggy.”

I couldn’t believe it. She had stepped into my world of making. And I had stepped into her world of waiting, standing outside, feeling the distance, rooting for her and at the same time wondering when she’d come back.

That role reversal gave us what years of explaining never could: perspective and empathy.

She now knows what it feels like to lose yourself in digital creation. I now know what it feels like to be left “outside” of it.

Yesterday and today we’ve reflected on this change in perspectives. I feel much more understood in my love for making and I feel a deeper understanding for how my deep-dives felt for her.

Thank you Lovable!

PS: One a side-note, I’m also in awe. In just three days, she fully iterated on her idea and built a solid product with actual non-trivial technology. I say this as someone who’s been doing this for 25 years: her app is getting really, really good.

@lovable PPS: Bumping in hope to hear if others have had similar issues or experiences regarding pre- and post-AI vibe-coding deep dives. @lovable has this come up at all on your radar?

Permalink · View on Twitter ↗
Reply
1 like · 333 views
In reply to @sama · Sep 4, 2025

i never took the dead internet theory that seriously but it seems like there are really a lot of LLM-run twitter accounts now

My personal analogy: The Internet today is now what TV became in 1999. And AI today is now what the Internet became in 1999. TV didn't go away but it was clearly and instantly relegated to second choice. The Internet felt more trustworthy and real. I wish I could put this more succinctly but, alas.

Permalink · View on Twitter ↗
Post
1 reply · 4 likes · 365 views · 3 bookmarks

tldr; @lovable helped her build an app. It helped me find compassion.

This week, my wife built her first app using Lovable. She finally felt what it’s like to get lost in the bliss of creating digital products, and I finally felt what it’s like to be outside of a loved one’s creative process.

For context:

My wife is an executive leadership coach. Her work is in-person, relationship-focused, and non-technical.

I’m a software engineer with 25 years of experience, and for me, making new things has always meant quality time with myself and learning.

But… The love for making things also put pressure on our relationship:

When I got absorbed in coding personal projects, I would vanish for hours, often days, hyper-focused, even thinking about the problem when off-screen.

So, even though I was physically “there,” my wife experienced absence.

She couldn’t understand why I poured so much energy into these side projects. And then my attempts to show her “the latest version” usually made things worse for her: too excited, too technical, too too hard to follow. And then, of course, I would feel misunderstood and alienated in turn. Yeah.

This week, something shifted. For the first time, my wife built her own app—with Lovable. She got hooked. She disappeared for hours, making, testing, playing around, chasing down bugs, refining features, obsessing over details.

Two days ago she sent me this:

“[…] since yesterday, the automatic cataloging of the photos and the recommendation engine have already been fundamentally improved, but right now the database integration is a bit buggy.”

I couldn’t believe it. She had stepped into my world of making. And I had stepped into her world of waiting, standing outside, feeling the distance, rooting for her and at the same time wondering when she’d come back.

That role reversal gave us what years of explaining never could: perspective and empathy.

She now knows what it feels like to lose yourself in digital creation. I now know what it feels like to be left “outside” of it.

Yesterday and today we’ve reflected on this change in perspectives. I feel much more understood in my love for making and I feel a deeper understanding for how my deep-dives felt for her.

Thank you Lovable!

PS: One a side-note, I’m also in awe. In just three days, she fully iterated on her idea and built a solid product with actual non-trivial technology. I say this as someone who’s been doing this for 25 years: her app is getting really, really good.

Permalink · View on Twitter ↗
Reply
535 views
In reply to @thesamparr · Aug 1, 2025

If I we’re 20 years old in 1945 there’s a chance I’d have 4 confirmed kills in the Pacific Theater.

Each generation carries a burden. But man we do have it good today compared others. t.co/CehYdgcZJh

@thesamparr My grandfather landed in Okinawa April 1945, GI, 69th Infantry Regiment. Having had only third-hand accounts of his experience, how did you calculate your chances?

Permalink · View on Twitter ↗