Instead of the benchmarks telling you how fast we are, check this out:
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Instead of the benchmarks telling you how fast we are, check this out: I built this whole site with GLM-5.3 Flash on Wally. The build was only 2 minutes, QA and fixes took 8 more minutes. 10 minutes for this quality is insane. Might never go back to Claude.
Posted by Shubham Malhotra (556 followers) 1 h ago · 3 likes · 132 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 几百页的书直接扔给 AI,长文总结经常容易丢细节。 — @bkdgiffug
- I talked at @AgentConf 2026 last Friday. — @Everlier
- Choosing the right agent skill is work. This CLI narrows it down. — @DanKornas
- 根据这篇文章制作了一个skill,还在打磨阶段,但已经可用 — @RevaHuai
- Writes attention-grabbing copy and removes AI writing patterns so the output reads like… — @tom_doerr
- Stop sending every coding task to the same model. — @DanKornas
- 资料太多、关系太乱的时候,可以试试这种思路。 — @bkdgiffug
- قصة من @latentspacepod مع Diogo Almeida (@CompleteSkeptic / TypeSafe) — الحلقة عدّت ~٢٤٠… — @hazemomier
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 20.8k posts from 5k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 11:08 UTC. Full method.