Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM 5.2 vs. Opus

techstackups.com

Post reply on HN
Print view View original

191–200 of 367 posts

Re: GLM 5.2 vs. Opus

#191

Post by newaccountman2 »

post-it wrote: post #180
cultofmetatron wrote: post #19

I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…

The streetlight effect: > A policeman sees a drunk man searching for something under a streetlight and asks what the drunk has lost. He says he lost his keys and they both look under the streetlight together. After a few minutes the policeman asks if he is sure he lost them here, and the drunk replies, no, and that he lost them in the park. The policeman asks why he is searching here, and the drunk replies, "this is…

[flagged]

Re: GLM 5.2 vs. Opus

#192

Post by toddmorey »

I’m actually amazed at the output since GLM doesn’t have eyes. If GLM 5.2 costs 1/5 as much, seems like it could be set up to reach out to a multimodal model for vision tasks when required. Closer to parity but probably still significantly cheaper.

Re: GLM 5.2 vs. Opus

#194

Post by scwoodal »

cultofmetatron wrote: post #190
scwoodal wrote: post #104

Earlier quoted context omitted.

> I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventions in the human reviewed spec. Guardrails/conventions should be enforced in linters, formatters, static analysis tooling; not specs/prompts.

lets say you have a table that is partitioned. how do you lint/format "any select into this table MUST include the partition key in the predicate and any join must include it in the on." I'm not personally familiar with any static analysis tool that does this but its trivial to implement with an llm prompt. trivially easy to add to your automated PR reviews.

I would tell the LLM to write a custom rule/check for whatever the scenario is. Then when the CI gate is run, all my custom checks get deterministically run.

Elixir is where I prefer to build software, so it would be creating a custom Credo rule.

https://github.com/rrrene/credo

https://credo.hexdocs.pm/adding_checks.html

Re: GLM 5.2 vs. Opus

#195

Post by veber-alex »

pietz wrote: post #66

GLM 5.2 has one big issue that will limit its meaningful success and that's the value of their coding subscription. Yes, in terms of API pricing, GLM 5.2 outperforms the competition. But the only people that use API billing for their coding work are large corporations, where these highly subsidized subscriptions are being fazed out. At the same time, none of these companies will use a Chinese API for their employees.…

The value of these models is that you can run them on your own hardware.

A company can buy a NVIDIA B300 and serve it's developers in house with unlimited tokens.

Re: GLM 5.2 vs. Opus

#197

Post by sanderjd »

post-it wrote: post #180
cultofmetatron wrote: post #19

I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…

The streetlight effect: > A policeman sees a drunk man searching for something under a streetlight and asks what the drunk has lost. He says he lost his keys and they both look under the streetlight together. After a few minutes the policeman asks if he is sure he lost them here, and the drunk replies, no, and that he lost them in the park. The policeman asks why he is searching here, and the drunk replies, "this is…

Sure, for casual evaluation, I agree. But are there serious analyses that are evaluating this kind of thing? I mean, these are the kinds of things I evaluate in my own work when a new model comes out, or when I'm evaluating a harness. But this is all very ad hoc and intuitional. I'd love to start bringing rigor to it, but I haven't found much prior art on this. In another thread someone said that's because it's probably impossible to do this rigorously because too much of it is subjective. And that does match my intuition. But I continue to suspect that intuition is wrong.

Re: GLM 5.2 vs. Opus

#198

Post by redsocksfan45 »

post-it wrote: post #180
cultofmetatron wrote: post #19

I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…

The streetlight effect: > A policeman sees a drunk man searching for something under a streetlight and asks what the drunk has lost. He says he lost his keys and they both look under the streetlight together. After a few minutes the policeman asks if he is sure he lost them here, and the drunk replies, no, and that he lost them in the park. The policeman asks why he is searching here, and the drunk replies, "this is…

[dead]

Re: GLM 5.2 vs. Opus

#199

Post by jdright »

not apples to apples. comparing official vs. pi.dev+openrouter and having slow times is more a openrouter issue. try comparing using official z.ai.

Re: GLM 5.2 vs. Opus

#200

Post by tw1984 »

miroljub wrote: post #99
cultofmetatron wrote: post #19

I seriously dont' know all this big hullabaloo about one shot prompting. by definition, a single prompt wont' constitute the complexity of a software project. ergo, what you'll get is a series of assumptions made by the model based on preexisting code in its training corpus. I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventio…

That's precisely the difference between an engineer and a business guy. The business guy would say "hey build me this and that" and would get _something_ to show of. An engineer will have a long conversation with a llm about the exact requirements, tech stack, tradeoffs. He would understand what is built, how is it built, and refine on the fly until he gets something sensible. It won't be as fast as "build this", but…

what you said above is only true when the AI is not as smart/professional/knowledgable as that engineer.
Post reply on HN