Smaller, faster, safer: running Kimi and GLM at scale • Hacker News Board

Re: Smaller, faster, safer: running Kimi and GLM at scale

#71

Post by lukan » Tue, Aug 04, 2026, 3:11 PM UTC

jfyi wrote: post #70

dceddia wrote: post #69

Earlier quoted context omitted.

Cloudflare could be the end of the open web and it seems crazy that more people aren’t worried about this. Turnstile everywhere + device attestation required is the direction this all seems to be headed. Because of all the AI bots of course (it is an excellent scapegoat).

It's pretty safe to say that most people don't know what cloudflare does, if they even know that it exists.

Pretty sure most people have seen their page at least once, so they know, Cloudflare is what they see if nothing is working (because the actual server is overloaded).

Re: Smaller, faster, safer: running Kimi and GLM at scale

#72

Post by lukan » Tue, Aug 04, 2026, 3:50 PM UTC

TacticalCoder wrote: post #28

brokenodo wrote: post #2

I was interested in reading this until my slop detector went off at the paragraph starting with “It's worth being precise about where the benefit comes from, because it isn't raw speed.” I love AI, but I really hate reading it.

> “It's worth being precise about where the benefit comes from, because it isn't raw speed.“ What's funny it's that is as if AI "learned" to speak english but not really. People simply don't speak using those strange constructs: those sentences sound a bit like if a "Karen" was trying to make a point. What's scary, to me, as a dev using AI, is that those LLMs do the same thing with code: it looks like proper code, bu…

"What's scary, to me, as a dev using AI, is that those LLMs do the same thing with code: it looks like proper code, but it really ain't so once you dig a bit."

Of course it always looks better, than it is, but it still works for me as in the code does what I asked the agent to.

Re: Smaller, faster, safer: running Kimi and GLM at scale

#73

Post by lukan » Tue, Aug 04, 2026, 3:54 PM UTC

WhereIsTheTruth wrote: post #63

The Cloud killed HW trust, SW is next One vCPU means nothing, which chip? which SIMD? what RAM speed? what storage? what latency? Quantization is the next layer of lies Society is moving towards offloading intelligence to clouid overlords, since nothing runs on your computer anymore, you can't trust anything And since datacenters occupy a physical space, they are building a monopoly defacto Unless transparency become…

"Society is moving towards offloading intelligence to clouid overlords, since nothing runs on your computer anymore, you can't trust anything"

You like sounding dramatic? There is a RAM explosion and big models already work on laptops. Some people will offload everything, some stay in control.

Re: Smaller, faster, safer: running Kimi and GLM at scale

#74

Post by spopejoy » Wed, Aug 05, 2026, 12:33 AM UTC

brokenodo wrote: post #2

I was interested in reading this until my slop detector went off at the paragraph starting with “It's worth being precise about where the benefit comes from, because it isn't raw speed.” I love AI, but I really hate reading it.

What's the tell, other than it butchering the context (bad writing)? The article as a whole doesn't seem horribly LLMy. The overall topic is pretty dry, and that sentence is honkingly bad, but not all bad writing is LLM-originated -- sometimes insufficient proofreading is at fault.