Both these models are not bad but you can not trust them to make good decisions. I meant GLM 5.1/5.2/5.3 in the previous answer, not the flash version
742 karma · joined July 3, 2014
Given how fast and cheap DS is, it's just an ideal model with enough "IQ" to let it loose. Another thing they left out of the article, DS becomes really good if you provide custom tools for the task, on it's own it's mediocre.
Much of joy we got from coding was taken way, I can not even imagine anyone wanting to get back to a coding role to vibe slop all day long.
I even heard from colleagues that presented algorithms better than the AI slop and heard verbatim from their boss: I prefer the AI solution instead of your.
So yeah, AI lunatics are ruining tech
Deal with one customer can be quite a nightmare, and honestly, sometimes using off the shelf solutions can result in saving time and money.
Even today I'm creating SaaS, not every problem is simple to solve. Take a look at CRMs, there are thousands of CRMs due to enormous egos wanting to build "my way", "the way", "the superior way", "our company is not like others (LOL)", etc. At the end of the day it's just a database with CRUDish UI.
My customers pay me to solve their problem well because they can not solve it themselves, when they do they just don't have the time.
Reality check: I have been coding many products with all frontiers models: Still takes a lot of time and, surprise surprise!, money for tokens. Ironically software development became more expensive for serious software that won't vibe-break/vibe-delete-prod/vibe-delete-database.
They try to push the narrative of having the best models but people finally discovered that Chinese models are actually great and a lot cheaper, I don't even think this is a reaction to GPT 5.6
Websites are surprisingly hard to maintain long term, specially for a broad audience of devices. Developer Experience can lead to better UX, the easier it is to build/maintain, the more likely we're to do it.
Given how bad AI is at design plus all the unstoppable slop train, I expect websites to become much, much worse.
Many people are complaining about the price but you can bring you entire steam game collection and even use as a PC if you want, I sold my PS5 once it became a useless brick cause Sony prevents you from running Linux.
Quite suprised this managed to be on HN first page with a fresh account.
Right now non-tech people just think AI will do anything they want and are the one in charge of hiring/firing, managing, etc. It's horrible to be a software dev right now, you've to deal with AI and lunatics.
Of course Domain Knowledge is important but, right now it's very hard to have reasonable conversation because... you know... AI this, AI that. I had a customer showing me a Claude vibe coded atrocity trying to convince me it's was a great app, now ask yourself: How are devs even supposed to collaborate with this without going insane? Simple, you can't.
Before we get local AI, we'll be using hybrid AI.
Running big models locally is unrealistic ($$$$$) but, if you imagine an Agentic Workflow where some bits run on the cloud and other smaller tasks locally, it's an amazing deal. You don't need Opus/Code/DeepSeek/Kimi/etc to do basic stuff that models like Gemma4:12b/Qwen-27b can do locally with much less latency.
Having a laptop where I can use a remote big model and combine it with 5 local domain specific models, is something I would love to do today. Imagine using OpenCode and you've a small model deciding which tasks run locally, then decides if you've a good local model for XYZ task or if we use a cloud model.
My main concern is: Is this hardware powerfull enough to allow local quick models switch? Unlikely but I hope I'm wrong
By "Working with the model", is essentially reading the ouput of prompts and pointing in a direction just to decide the next steps. You could try to increase the prompt limit and create an agent that explores multiples directions in a DFS manner.
The issue with vulnerabilities is the agent not knowing when to stop because it's hard to validade if you reach the final result or not. I get amazing result when I code with AI, letting the AI go wild is just a waste a time and tokens.
I recommend you to read the write up on the crackme (https://crackmes.one/crackme/698f40f1e2ba6023bfacaa82), I think most experience developers would need, at least, 2 months of learning reverse engineering techiques to hopefully crack this one. GLM 5.1 manage to solve it, it didn't "copy pasted" any answer from it's training data. It did a binary analysis, anti debug patching, patching binaries, debugging memory during runtime etc. It only took about 20 minutes.
After seeing what GLM did, I do believe Anthropic concerns about Mythos are real. Cracking software just became a lot easier, too easy for my taste. Video games cheats will be the norm, cracked desktop apps without licenses and infected with malware. It's not a new thing but it just became too easy.
I've used glm 5.1 on fairly advanced crackme challenges (example: https://crackmes.one/crackme/698f40f1e2ba6023bfacaa82), and to my suprise it was able to patch binaries, doing runtime analysis, bypassing anti debug techniques, etc.
Expecting the model to do everything by itself is unrealistic, I found that working along the modal works really well. I'm not speaking about spoiling the solution, just tell it which direction to explore. Chinese models are much more capable than people give it credit for, but Claude/Codex won the marketing game.
The only usecase of this methodology would be for CI integration, which can be nice but I think security reviews still need human attention and expertise.
Seeing this happening in trusted CLI tools makes me wonder what will happen to Linux
I’m actually building better UIs just because it became less time consuming to do so.
There is just a super noisy minority that spams the internet with slop so bad that no one can take their product seriously.
Z.ai does recommend to use claude cli as a harness for GLM5.1, I still get good results with opencode.
Chinese models are really quite good at a lot of stuff.
Input (Cache Hit) Input (Cache Miss) Output mimo-v2.5-pro $0.0036 $0.435 $0.87
mimo-v2.5 $0.0028 $0.14 $0.28
It looks weird/ugly because electric cars no longer need to be longer and have enough space for massive sport engines. Maybe we'll get used to it over time, still I would prefer the front of a Ferrari 458
The interiors look really nice, I'm a fan of the dashboard elements, blending touch with actual physical buttons.
Porting to a safe language without the safety features.
Imagine reviewing CQRS without having built one
This idea of reviewing an architecture that you never coded is just a fantasy.
At some point in time, me and a lot of people, thought that using Redux was a great idea until we had to manage verbosity and middlewares. Now we had to deal with the consequences of our decisions and we learned.
I also think this article is just a rage bait
Today I'm forcing myself to learn SwiftUI and type each character with my hands, there is a part of me asking "Why are you wasting your time instead of prompting it and getting the UI you want in minutes?". Well, even I use AI I must know the domain I'm operating in to create good products instead of useless slop. Even though I've been coding for 20 years now, I still need to be humble to grown in anything new. I can vibecode full apps but I'm not gonna pretend that my experience isn't playing a massive role in guiding the models.
Don't let AI take away your joy for building stuff, it's totally fine not being "productive" and taking your time. Just force yourself to have, at least, 2 AI days off every week.
I've tried both Opus and GPT 5.4, they also hallucinate just like the rest at a much higher cost.
The more you use a model overtime, the better you become with it. It's really hard to measure, my main metric lately has been tokens per second/time to complete task.
At this point I've the feeling frontier models are optimizing for benchmarks and one shot prompts.
China is leading in open source frontier models, so I don't really see how the US wins this one. At some point, companies and people will start running their own models in the cloud and locally, Chinese models will be everywhere.