Agents have made me completely stop using IDEs with LSP
I just rawdog vim + tmux + rg + fzf and that's all I need
I really value just being able to pop open a tmux pane and open the code in vim quickly and stay close to agents and not wait for LSP or other plugins and shit to start up
Autocomplete is useless to me now since I write way less code by hand, and bc I write way less code I have enough working memory slots to just raw dog that shit it if need be
Go-to-definition is less useful since rg + fzf with some configuration is fast enough for 90% of my use cases, if I'm bottlenecked by these tools it means I'm on a deep enough dive that asking agent to read the code and show me key files+lines for me is more efficient (even if I had go-to-def)
Also there's no replacement for understanding now, so I find intentionally using tools that require building a mental map and understanding of codebase to use efficiently is pretty useful and keeps me from completely vibecoding and having zero understanding of wtf is going on
Also these days I'm always up in a VPS ssh'd into it so having my tooling work fast and well in terminal with configs I can just copy+paste is nice
Today is a hard day. I shared this note with the @linear team today: We’ve made the difficult decision to increase our workforce. This is not a cost-cutting exercise or a reflection of anyone’s performance. We’re simply reimagining every role for the agentic AI era. We’re hiring. We’re sorry about that.
.@Uber Q1’26 earnings are out — we’re off to an exceptional start to 2026:
✅Third straight quarter of 21%+ Gross Bookings growth
✅Non-GAAP EPS up 44% to $0.72
✅Nearly $10B of TTM Free Cash Flow — a record high
🥇Membership joined the 50/50 club — 50M members, 50% Gross Bookings coverage
🏋🏻♂️No skipped reps — delivering on our Mobility barbell strategy (low cost + premium)
💰Record $3B in share repurchases
Looking ahead, our product innovation, AV leadership, and AI momentum have us well positioned to accelerate the power of our platform. Let’s #GoGetIt!
https://t.co/t8EfDL0I7C
In 10 years, we'll realize young adults can't read, write, or think as well as they should. We'll wonder how we allowed students to offload huge chunks of their learning to AI. Today we're just watching it happen. This is the most obvious unforced error of our time.
I'm 22 years old and Claude Code is deteriorating my brain.
Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me.
In convos with a couple of friends, it's been a point that's been brought up pretty frequently.
None of us feel as sharp as we used to.
I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot.
P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless