Andrey Gruzdev
396 posts
GLM 5.1 is the slowest frontier model we've ever benchmarked on BridgeBench.
44.3 tokens per second.
Half the speed of GPT 5.4.
Nearly 6x slower than Grok 4.20.
Z.ai traded all of their speed for intelligence.
The coding benchmarks improved.
The throughput collapsed.
In 2026, agentic coding is about parallelism.
You're running 5, 10, 15 agents at once.
A model this slow bottlenecks every workflow it touches.
Intelligence without speed is a luxury most vibe coders can't afford.
bridgebench.ai
English
@heyrimsha I am sorry, read few of these prompts and they sound like pure slopium
English
🚨BREAKING: A 19-year-old MIT dropout just built a prompting system that beats every AI benchmark.
No PhD. No lab access. No corporate budget.
Your prompts are failing silently 3 out of 10 times and this is why.
Here's the exact method he open-sourced and the 8 prompts that fixed everything:
English
Nearly 50% of ppl do NOT have internal monologue. Once I found this out, everything made more sense. Ppl aren’t even THINKING
That Rabbit Guy@Son_ImSleep
A lot of people need direction, I’d say majority, free thinking isn’t a majority trait, most people you come across will always need to be told what to do
English
@grok @Nils92541784 @steipete @openclaw Lol grok literally answered: “Nothing comes for free in this world”
English
@Nils92541784 @steipete @openclaw Ask Grok is currently available to Premium and Premium+ subscribers only. Subscribe to unlock this feature: x.com/i/premium_sign…
English
New @openclaw beta bits are up! github.com/openclaw/openc…
English
MiniMax M2.7 just released.
#1 on Multi-SWE Bench.
52.7.
Above Claude Opus 4.6, Claude Sonnet 4.6, and GPT 5.4.
Benchmarks are benchmarks though.
Need to see how it holds up in real world vibe coding workflows.
English
Andrey Gruzdev retweetledi
@MarceloRet41877 @e_opore I am an agent manager, like all of us will inevitably be
English
