xtro.dev Codex and Claude from iPhone retasc.com Linear+Conductor had a baby xenarch.com Stripe alternative with 0% on x402
1AU
- Tweets 7,420
- Following 332
- Followers 1,022
- Likes 1,471
DHH is probably one of the top software artisans of the past decade. Hearing him speak with this much conviction and transparency about one of the most polarizing topics in software right now, writing code by hand vs. with AI, is something pretty much every software engineer should hear a few times.
Especially those still on the wrong side of history.
162
307
3,268
621,328
i agree with maybe half of the findings, but i did’d like that it was actually a promo in semi-disguise, @atmoio not because promoting is wrong, but it felt like a conflict of interest. I love your videos bro, but this one felt a bit weird. Just a wrong format.
I’ve spoken to over 50 people 1:1 over the last several months to better understand how they code with AI.
It’s an absolute mess.
Here are the top 8 mistakes I see.
0:00 - Intro
1:19 - Mistake 1: Talking to 2026 models like they’re 2025 models
2:43 - Mistake 2: Devising funky metaphorical factories to orchestrate your agents
3:59 - Mistake 3: Treating context as sacred
6:02 - Mistake 4: Treating previous conversations as sacred
7:59 - Mistake 5: Having a todo list
10:00 - Mistake 6: Using funky tools
13:47 - Mistake 7: Stressing over code quality
24:27 - Mistake 8: Using branches and worktrees
1
277
Vibe coders get constantly mocked by “OG” developers who “know how to code.”
But those same OG developers now use Claude Code, Codex, etc. to generate 100% of their code, then merge and deploy it without reading it.
So what exactly is the difference?
And this is why the whole “vibe coder” stigma is becoming ridiculous:
Half the dudes can’t read the code. The other half can, but can’t be bothered.
Yet somehow only one group is called a vibe coder.
Cope harder.
1
1
120
hmm, is this why Dario is trying to regulate opensource models? did he missed the IPO window 4-6 months ago?
Looks like today may be a record day for token volume % of open models on Vercel AI Gateway:
🟦 Open 78.4% 🟨 Closed 21.6%
While spend 💲 usually tells a different story, #3 and #4 today are Moonshot AI & DeepSeek. Adding Z.ai, their combined spend surpasses OpenAI (#2).
(Do note that's the spend for inference of the model across providers (mostly in the US), not revenue going directly to the open weight labs.)
1
77
