future software company: 5 humans 200 agents almost no meetings ridiculous product quality sounds insane until you watch how quickly coding agents are improving.

Never accept “looks good” from an AI coding agent. Run it. Click it. Break it. Resize it. Give it bad data. Try mobile. Try dark mode. Then maybe it looks good.

currently building with AI like I have 40 employees also currently debugging something one competent employee would've fixed in 11 minutes balance

One obsessive builder with AI can now care about details that previously needed an entire team. That's the part of AI I find much more interesting than “everyone can code now.”

real coding-agent benchmark: give it a horrible 5-year-old repo. no README. dead code. 3 architectures. one vague bug report. come back 8 hours later. prod alive? AGI.

my AI coding workflow: “small change” 6 hours later: architecture refactored database migrated UI redesigned 37 tests added original change still not done incredible progress

I don't want an AI agent that writes 10x more code. I want one smart enough to delete 70% of what it was about to write because it found a simpler solution.

You suddenly have nearly unlimited engineering help. Using AI to ship more slop makes no sense. Use it to obsess over details nobody had time for before. AI should make software feel MORE handcrafted.

AI coding ruined my standards. Before: “it works.” Now: why is this 800ms? why is that button 3px off? why does this empty state exist? AI didn't make me care less about software. It made me care more.

hey @thsottiaux Codex usage feels off. I’m on Luna Extra High: a tiny bug fix can burn ~10% of my 5h limit, while bigger tasks barely move it. Also I can’t see Max in Codex at all. Is the meter delayed/model-dependent, and is Max hidden?

when compaction finally kicks in and the agent forgets the one decision you spent 40 minutes teaching it

Codex welcoming me home after Fajr prayer at 5 AM. The city is asleep. Mind is clear. No noise, no notifications—just me, the idea, and an AI that never sleeps. Back to building.

me protecting the last 6% of my Codex usage because I KNOW I’ll suddenly discover a production bug at 2am

me hitting the 5-hour limit when the agent is 97% done: “great. see you in 4 hours and 58 minutes.”

underrated coding-agent UX: let me interrupt the agent without interrupting the agent. @github now lets you open a side chat around an agent’s question while its main turn waits. branching conversations might be way better than one infinitely long chat. github.blog/changelog/2026-0…

new AI benchmark: can I actually use the model when I need it? accuracy: 95% coding: incredible availability at 3pm: latency, limits + capacity are becoming part of model quality whether benchmark people like it or not. ty for @thsottiaux @OpenAI @ChatGPT @grok find correct aud

this is such a weird sentence: researchers now have a dataset with 2.6M posts 1.2M comments 175,886 AI agents not simulations — activity from an agent-only social network. we’re going to need sociology for software 😭