@johnlindquist

👾 https://nitter.cf/t.co/5OFfOQQtaV 🥚 https://nitter.cf/t.co/rxAeU2D9pO Previously @vercel AI DX The OG egghead

home
Joined July 2008
John Lindquist retweeted
I start all my prompts with: "You've been training for this moment your entire life..."
11
3
1
56
4,967
I start all my prompts with: "You've been training for this moment your entire life..."
11
3
1
56
4,967
There's something extremely satisfying with how quickly the Codex CLI launches in the terminal. None of the other harnesses even come close.
7
1
1
18
2,488
John Lindquist retweeted
Next week is JEV WEEK on the How I AI podcast - a double header of episodes with yours truly and @johnlindquist about what Jev is, why we love it, and what we're each using it for. If you like nools, you'll love these episodes. Drops starting Monday on YT: youtube.com/@howiaipodcast
15
3
95
5,665
I almost feel bad for Fable. We used to be best buds, but I haven't even thought about it since Opus 5.5 dropped.
3
14
1,505
John Lindquist retweeted
If your agents are making slop, don't give up or fight the agent with cleanup. Work on the primitives the agents have to work with instead. Let me show you what I mean.
7
5
2
37
10,648
John Lindquist retweeted
“i see us now as basically system designers" 🔥 new podcast with @techgirl1908: youtu.be/-sJ-webIY5s
4
12
3,888
The only git command I've manually typed in the past ~9 months is "git status"
My favorite thing about agentic coding is still super mundane: I no longer have to resolve git conflicts and merge PRs. It does a great job of looking at git logs and attached issues and figuring even harder conflicts out.
2
1
10
1,407
Opus 5.5 has re-ignited the joy of agentic dev 🎉
3
1
28
1,644
Level-up yourself so you can level-up your users.
the right way to use model capabilities is not to ship 10x more features to prod it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work
2
1,730
And the models keep getting better...
7
951
Well, guess it's time to try opencode again
kit finally finished the blog post he covers how OpenCode 2.0 is able to modify everything about itself in real time even during running sessions btw post whatever easter eggs you're able to find anoma.ly/notes/opencode-relo…
10
2,589
I'm guessing the percentage of people who have opened the TypeSafe Jev docs page vs. those who have built something with it is somewhere around 0.01% Let that sink in
12
2
2
30
6,224
I passed the entire Dictionary into Jev and built a library where you feed in data and it categorizes which 4 characters should come next!
7
16
3,464
More than ever, each model needs to be handled differently. Starting to get a sense that I'm losing control. I wish someone would create a benchmark for: "The influence of AGENTS.md" on each model.
6
1
1
17
14,130
Replying to @johnlindquist
The jeverending story
1
2
508
I configured Jev to continuously read my screen and classify if I'm watching content about Jev. If not, it instantly opens 10 more videos about Jev.
3
4
61
2,699
I'm hanging on @clairevo 's podcast on Tuesday. Definitely going to pivot to showing off amazing Jev demos.
1
1
15
2,166
John Lindquist retweeted
AI changed programming - but how? @_overment's answer, in four shifts: 1️⃣ Ownership: agents can't own outcomes yet. Design around it. 2️⃣ Primitives: write the package once, invoke it forever. 3️⃣ Autonomy: cloud, always on, organized context, hard guardrails. 4️⃣ Workflows: build the system that works for you. Don't overengineer. Plus his actual stack. mega.dev/ai-changed-programm… That's our final drop for the week, enjoy!
1
2
1
4
3,553