Nine coding agents running, nothing shipped: the "agent mania" post every developer recognized
SummaryThariq Shihipar, who worked on Claude Code at Anthropic until this month, says coding agents can put you in a mania where you feel busy all day and nothing really happens. His guess: it is often avoidance of something else.
· MODEL Editors · 1 min read
Some links may be affiliate links. Disclosure
On Thursday afternoon, Thariq Shihipar posted two sentences on X that a lot of people who use coding agents seem to have felt in their chest:
"There's 100% a kind of mania you can get into with coding agents, where it feels like you're getting a lot done and working all the time but nothing is really happening.
I think it's often a form of avoidance of something else in life."
Who said it. Shihipar (@trq212 (opens in a new tab)) worked on Claude Code at Anthropic for more than a year. He announced he had left the company on October 23 (Pacific time), and his X bio now reads "formerly Claude Code @anthropicai." He has not said publicly why he left, India Today notes.
Why it spread. The post went up at 3:42 p.m. PT on October 29. By midday Friday it had passed 1 million views, with about 14,600 likes, 700 replies and 400 quote posts, per X's public counts. India Today wrote it up on Friday morning, and it was a trending topic on X.
What he did not say. He didn't say coding agents are useless, and he didn't cite a study or any numbers. It's an observation about one way of using them: lots of agent activity, very little that ends up finished.
The joke in our cartoon. The nine agents, the 212 commits and the unopened email are made up. That was the point. The quote at the bottom is real.
Our take. Agent dashboards are great at measuring motion: sessions, tokens, diffs, branches. None of those are the same as shipping. A quick end-of-day check: what did a user, a customer or a teammate actually get today? If the answer is "nothing yet, but 14 agents are at 99%," it might be time to close the laptop and open the email.
Sources: Thariq Shihipar's posts on X (read October 30, 2026), India Today (October 30, 2026). Not sponsored; no affiliate links.
MODEL Editors
Sources
FREE · EVERY WEEK
The top AI tools this week, tested.
Every week MODEL's editors pick the AI tools worth your time, try them hands-on, and tell you what's good, what's not, and who it's for. Free, in your inbox.
Free. Unsubscribe anytime. Our picks are editorial and can't be bought.
Continue
AI News
Elon Musk: "The people deserve to have their RAM too!" (after Altman's 5% DRAM line)
Two days after OpenAI's CEO called home DRAM "quite terrible" on Cheeky Pint, Musk replied on X with a one-liner that racked up millions of views. We already covered Altman's quote. This is the sequel.
· MODEL Editors
AI News
YC told 50 AI agents to build a Minecraft civilization. They built a bureaucracy
In a YC Labs and Olam Labs experiment, 50 GPT-6.1 Sol agents got three hours and one goal. They ended up with permits, a ration ledger, and four agents spending 11 minutes appointing a "sole fertilizer operator."
· MODEL Editors
AI News
A ghostwriter's own writing got flagged as AI. Here's what detectors can and can't tell you
NPR reported on Oct 31 that a writer lost out on a book job after detectors flagged a sample she wrote herself. A June study of four popular detectors shows why one score should never decide a case.
· MODEL Editors