DeepSeek-v4.1-Flash-1017

What if those “cost implications” are just asking Opus 6.7 to fix whatever issue cropped up?

> haven't fully realized/felt the cost implications of trainwreck software yet

As long as the API is private or not dependent on by automated systems and you have good test coverage, you can get away with bad code IMO since you can always refactor. If it looks stupid but it works (and can be refactored/fixed/improved later if needed) it aint stupid.

IMO the fundamental principles and "conflicts" are still the same, but many have forgotten about them with all the hype and sense of speed. The industry will slowly rediscover them.

Support burden? When did companies care about customer support or system maintenance?

They already did the bare minimum allocation to both despite engineering screaming at them.

I highly doubt executives are going to accept slower release and sale cycles in order to provide better support.

If anything, I expect this trend to accelerate. I’m imagining the opposite, a plethora of AI slop with increasingly burned-out engineers.

Yea, this is one thing that gets me. Vibe coding and freestyle prompting gets wildly different results. Starting from a set of specs and expectations routinely gets me reviewable and we'll tested code. Sure, running the full test suite alot slows things down and uses more tokens, but when I hit a five hour or weekly window, I just roll up my sleeves and start working without the model because the code is layed out the way I expected and is designed to fit my meatbag workflow and pace.

You must not be looking very closely yourself then.

Anecdotal but I was doing regular adversarial reviews of new work using about 5 models (mostly the open Chinese ones like DS, GLM, Qwen, Kimi, etc) and GLM routinely took much longer for similar results and the same instructions.

It would just loop on things and go down rabbit holes more. DS flash has been so consistently good I've kinda settled on it for 90% of my work.

I still use adversarial review for bigger changes where I want to make sure any issues are caught early, but I genuinely feel as tho if no new models ever get made I'd be fine with just using DS forever.

It wastes my time. A lot! In different ways. That's the tl;dr. Really.

Keeps repeating things I settled as accepted or rejected. But what really gets on my nerves? The language it uses – that aweful, useless typical LLM languages! No AGENTS.md instruction, no per session instruction, no just two-prompts-prior instruction seems to work, hell sometimes instruction regarding that in same prompt doesn't work. GOOD/BAD example along with instruction don't work. That wastes time and zones you out! Not to mention the fatigue of to and fro. DS has been working much better. Hell Gemini 3.1 Pro works so much better than GLM. I don't have extended experience with OpenAI and Anthromic models but the free claide.ai works quite well and better than GLM 5.3 (not even flash). Albeit I must say I rarely use claude.ai for coding, but technical tasks? All the time!

GLM's best response: "No excuse. My fault. You exactly asked me not to do exactly that and so did the AGENTS.md. I failed". Love it. Except that if I press I will get that response every 5 prompts.

For me GLM thinks too much for no reason. It takes a 2-3 turns for DS where for GLM it takes up to 10.

I like giving precise instructions,”update function xx to support input yy, add tests”. There is no reason for 10 turns and 5 minutes of waiting.

> the first thing I noticed was how slow it

This really depends on the provider, it's a very fast model with ours

Reading quickly, I thought the open CoT was the most important piece of comment, probably just bc that seems like it would be the most useful to me.

debugging reasoning traces more effectively seems useful to find prompt issues writing custom harnesses even if it runs on stronger model later

This number reports, basically, how good it is to live inside a country, while the comment that you are replying to is entirely a list of foreign policy complaints (regime changes, etc).

It's kinda like meeting someone on the street who's protesting about animal cruelty in slaughterhouses, slyly handing them a chart showing them the nutrition facts of beef, and then walking off without another word as though you've settled your case.

Like, I get the point you're trying to make, but I hope you're aware it's a non-sequitur in context?

Why link to a number, which means roughly nothing, instead of the specific details on the countries you're trying to compare? I have no idea how to break down or make my own assessment of what 0.83 or 0.18 means. Does that 0.83 for the US include all of the people being shipped off without due process to El Salvador, or do they count that as part of El Salvador's Human Right Index?

People like to bring up the Uyghurs immediately, but never really have the same smoke for the US. Also, do we include the prison population in human rights? Do we include access to healthcare? What about systems perpetuating poverty like lack of access to public transportation?

To pre-emptively be clear on my stance or potential bias, I stand by no country in the world. I was born in Iran, and my parents left when I was young to the US because they believed in the American Dream. The irony being that the dominos of why they left were initiated by the US and UK. And long before Trump was elected, but certainly immediately afterwards, I decided to leave the US once I had the means. (Also because of the lack of public transit, the $100k medical bills after an accident, being punched by a homeless person, and having my possessions stolen repeatedly and the cops giving me a :shrug:). I moved to Japan, where I experienced blatant racism for the first time. I moved to Hong Kong (and tbh no real complaints so far), but I am technically subject to the freedom of speech constraints on China.

I have no allegiance to any country or specific people. My allegiance is to all living beings.