We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality:
- GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81)
- Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls
- GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build.
Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!
So what happens when you're forced to? Admission is one thing, action is quite another
But it is by admission that action is possible. Often, it is not about "living inauthentically". It is often just about "living"
It is mostly the little things that matter. The detail which everyone missed. The small bit of insight obvious only after a small gesture. Things left unsaid
Such things often speak of deeper truths. Truths most aren't comfortable admitting, much less confront
"Akal" dan "logik" yang digunakan ahli "falsafah" pada zaman pra Newton memberi natijah berbeza daripada kefahaman moden.
Sebab yang tertinggal adalah autoriti Aristotle.
1/ Recently, there was a sudden uproar in twitterraya criticizing the practice of Islamic Banking.
The uproar was a result of a twitter space event by @magmalaya inviting Safdar Alam to explain his views about riba and Islamic Banking,
Heard abt the time a group of students stood toe to toe against the University, and incredibly, won? They recouped RM millions in compensation.
This is the astonishing story of MJIIT-Voices and UTM, which I witnessed first-hand as Director of Students at MOE in 2019.
🧵
We are looking for 100 participants and changemakers!
Grab this opportunity to learn about policymaking process. We are targeting Malaysian youth who are aged 18 and above and passionate about policymaking issues
Visit
https://t.co/dnTIIlASOC