Really!? Glm5.3 is my daily driver and I feel im having the most productive experience with agentic collaborations so far, by a lot. Using pi with tons of custom extensions, that to be fair I developed since making the jump off of codex and claude about 12 weeks ago.
I primarily do not write code for a living. I do a lot of modeling and commercial analysis and a lot of math (related to differentiable simulation)
Same here. Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result. Mainly, it doesn't hallucinate and convince itself of mistake so it's good at retrieving information or asking the user for it. Opus and Fable always state something, then try to "prove" it but end up convincing themselves of the wrong thing. Having subagents for retrieval and validation helped but were not enough.
It will also fully ignore you if it has the slightest belief (not even a hint) that it knows what you want better than you and just start doing things.
This is also why I think it's baffling that they switched to auto mode by default. It's becoming harder to use Claude at least to help with improving at coding.
If I ask something like:
"I'm building a simple X as a learning exercise, I'm writing the code so please only answer the question I'm asking and don't try to solve the problem directly. How does ..."
There's a 30% chance it starts reading and writing code immediately and a 20% chance it argues with a "design decision" that will bite me in the non-existent future of my learning exercise. If I ask a follow up question, naively assuming that the context from my original question still stands without repeating, it will almost assuredly start making modifications to my code.
Full GLM-5.3 needs a beast of a system, but you can run GLM-5.3 Flash on the 2x Spark setup the GP comment mentioned. If benchmarks are anything to go by, Flash is like having a local Terra-tier coding model: https://artificialanalysis.ai/models/comparisons?compare=glm...
I’m also pretty happy with GLM 5.3 Flash (for coding, navigation and german language it sucks at). Incredible that you can run it on a fairly practical (seeming) home setup.
But here’s the standard question: At what speeds/other limiting factors?
I’ve heard this about mechanical electronic signage used for team dashboards 30-40 years ago.
You’d sit in the office with your back to it and the clicky clacky sounds would be going every so often when the content updated. but people would know the specific clicky clacky sound that required them to turn around and read the sign based on their job function.
I’ve also heard of day traders mapping stock tickers or other data into sound and having headphones on all day with it
Interesting point. I think there might be something special about sag given the way Hollywood does business. Everyone switches employers constantly as projects spin up and wind down. Having a mostly permanent role in an organization is super unusual - and I wonder if these roles (like a 20 year soaps gig or the simpson’s) have different stats on working on/off the card.
> Interesting point. I think there might be something special about sag given the way Hollywood does business. Everyone switches employers constantly as projects spin up and wind down. Having a mostly permanent role in an organization is super unusual […]
And yet all the major US sports have player associations/unions with minimum salaries. The players are hardly constantly switching, and when they do switch it's often not their own choice but rather their employer/team trading them.
reply