[flagged]
GLM-5.2 is a step change for open agents
81–90 of 240 posts
Re: GLM-5.2 is a step change for open agents
#82I've been working with Deepseek V4 Flash (with opencode as the harness). It's been almost indistinguishable from Codex / Claude Code for me. I'm sure I'll run into problems when I get to a stickier ticket to tackle. But so far, it's been quite good, and I find it writes straightforward code. I do think the Chinese models are good enough for an 80/20 rule use case.
I tried Deepseek V4 Flash with very low expectations and was pleasantly surprised. It's a surprisingly capable model for the price.
What provider(s) do you use?
Re: GLM-5.2 is a step change for open agents
#83Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…
You made me realize something. I routinely spend upwards of 500$ per month on LLMs for coding (expensed towards clients). However I live in a place where 500$ is around the avg. salary. I’m lucky that I know my way around western clients. Clients who pay these expenses and are happy to work with me because I am still about 50% cheaper than local talent in EU/US, while my salary at home converts to an upper class inco…
Thanks for sharing your insight.
Mind if I ask you for a few vibe coding tips? I failed to solve you gh puzzle in the profile though.
Re: GLM-5.2 is a step change for open agents
#84GLM-5.2 has been a step change in how fast i can burn through tokens. I subscribed to their max plan to try it out. It counted me 700M tokens and drained my weekly quota in under 2 days. Quota just reset less than 24h ago and i'm already >60% weekly quota usage. For reference the kind of work i did would have used somewhere between 3% and 5% of Codex max or Claude max. The model is good, the plan is a scam
Kimi and GLM models have coined a new term: Thinkslop. They run a chain of thought that is up to 10x longer than other models and it seems that through a lookback mechanism they are able to use the CoT to reason about solutions to tasks they couldn't otherwise solve.
The downside is of course that they consume many more tokens off your plan, and also that they are significantly slower. Kimi K2.7 takes about 7x longer to finish the same benchmark tasks as DeepSeek V4 Pro on my router benchmarks (https://role-model.dev/).
So for now I'm happy with just two models: GPT and DeepSeek.
Re: GLM-5.2 is a step change for open agents
#85I signed up to a z.ai max account, $144. Hardly been able to use it as it 429s on most requests. They’re also refusing to refund me.
Self-promo but you should try our service synthetic.new. We generally have up-to-date open-source LLMs on the sub, and we have GLM-5.2 :) Perf+stability should be wayyy better than zai.
Re: GLM-5.2 is a step change for open agents
#86Here are the numbers from their bar chart: 1. SWE-bench Pro Model Score (%) GLM-5.2 62.1 GLM-5.1 58.4 Claude Opus 4.8 69.2 GPT-5.5 58.6 Gemini 3.1 Pro 54.2 2. Terminal-Bench 2.1 Model Score (%) GLM-5.2 81.0 GLM-5.1 63.5 Claude Opus 4.8 85.0 GPT-5.5 84.0 Gemini 3.1 Pro 74.0 3. NL2Repo Model Score (%) GLM-5.2 48.9 GLM-5.1 42.7 Claude Opus 4.8 69.7 GPT-5.5 50.7 Gemini 3.1 Pro 33.4 4. DeepSWE Model Score (%) GLM-5.2 46.2…
> What _is_ Google DeepMind doing
I feel like it has been pretty visible about what’s happening, between their press and products and financial statements. It’s just not what people are accustomed to expect.
First, Google has become a major compute provider for competitors, thanks to TPUs. They’ve talked about allocating TPUs to GCP instead of their first party products. I can only assume it’s because they’re collecting a higher margin, and it covers the cost of data center buildout - which they’ve been aggressively doing. I wouldn’t be surprised if they made the financial decisions to delay or slow training for Gemini 3.5 when they provided last minute compute to Anthropic this spring.
Second, Gemini has very directly not been focused on agentic coding, maybe 3.5 Flash being the change. They’ve built models they can deploy to watch YouTube videos, Nest cameras, scale to AI in search, understand fitness info in Fitbit, etc. They’re very clearly not focused around agentic/coding. They’ve put in a ton of efforts into multimodal data in and out, and they’re the only major lab working on video generation still. There was leak/rumor that their cofounder (brin) was getting involved in the model training to renew focus on agents so maybe this will change, and again 3.5 already feels different.
Re: GLM-5.2 is a step change for open agents
#87I just tested GLM 5.2 out via Z.ai in pi for a little one-off project that was already scoped. It actually did a relatively decent job starting out, and figured important things out from context. But the reasoning traces became increasingly hilarious, with it getting confused and going in loops, doubting itself. I began to feel almost sad, it was like listening to the internal monologue of someone with anxiety disord…
The reasoning traces always look terrible and they’re frustrating to watch. It’s the same with Kimi. What’s interesting is that the end result is then good. I think it’s just some sort of devils advocate trick to get better output.
thinkslop recursion.
Re: GLM-5.2 is a step change for open agents
#88GLM-5.2 has been a step change in how fast i can burn through tokens. I subscribed to their max plan to try it out. It counted me 700M tokens and drained my weekly quota in under 2 days. Quota just reset less than 24h ago and i'm already >60% weekly quota usage. For reference the kind of work i did would have used somewhere between 3% and 5% of Codex max or Claude max. The model is good, the plan is a scam
Kimi and GLM models have coined a new term: Thinkslop. They run a chain of thought that is up to 10x longer than other models and it seems that through a lookback mechanism they are able to use the CoT to reason about solutions to tasks they couldn't otherwise solve. The downside is of course that they consume many more tokens off your plan, and also that they are significantly slower. Kimi K2.7 takes about 7x longer…
yeah Kimi K2.7 was doing ok but was painfully slow. The coding plan limits were good though.
I haven't tried deepseek yet, i should check this one out.
Re: GLM-5.2 is a step change for open agents
#89It's by far the most competent open model I've tried yet. It's a bit slower than Claude, but in terms of coding capability it seems to get comparable results at least for the work I'm doing.
Re: GLM-5.2 is a step change for open agents
#90I just tested GLM 5.2 out via Z.ai in pi for a little one-off project that was already scoped. It actually did a relatively decent job starting out, and figured important things out from context. But the reasoning traces became increasingly hilarious, with it getting confused and going in loops, doubting itself. I began to feel almost sad, it was like listening to the internal monologue of someone with anxiety disord…
The reasoning traces always look terrible and they’re frustrating to watch. It’s the same with Kimi. What’s interesting is that the end result is then good. I think it’s just some sort of devils advocate trick to get better output.
The reasoning tokens are really just there to extend the amount the LLM can "compute" the problem; put another way, the only way a given model can "think" more about a problem is to fill more of its context with predicted tokens, which has the effect of increasing the accuracy of each token. The reinforcement learning these models go through generally doesn't care what the chain of thought tokens look like (outside of preventing loops/gibberish/reward hacking), only how good the final answer is - so while it does look something like "reasoning" to us and has a rough correlation with the final answer, treating it as actually representative of what the final answer will be or an actual thought process is giving those tokens too much credit :)