I dislike this approach. In my opinion it is much useful a 1x/2x billing based on hour like Deepseek does. Being unable to use it at the hours I need it makes me want to remove the service, not upgrading it.

Now, if I could afford 4...

That is how you get a hardware provider to stop selling you stuff

Personally I have been using Deepseek V4 flash and it is enough for my needs. You can use OpenCode Zen/Go and also get access to many other models, including OpenAI ones. Writing purpose specific agents can make cheaper models close the intelligence gap with the most expensive ones

I'm suspecting it is Deepseek flash-vision-exp V4

Unless it's an avant-garde A/B test with two endpoints targeting the same model, we now know it isn't.

no, and in fact they should be extremely easy to detect if they are substituting a token that is a least-probable synonym

I practically switched to doing everything with Luna or DeepSeek V4 flash. I haven't feel the need for the more expensive models.

I am in the same boat as you. I am using Luna and DeepSeek Flash. Both super fast, super cheap, and I have not felt need for anything more capable in few weeks.

I'd like to try DS4 if Cursor adds it

I'll use it locally too, but we use Cursor for work

Of the two, which do you find better?

I really, really like DSv4 Flash because you see the full, real thinking text. That’s been so useful for helping steer the model; as well as seeing its thoughts and correcting any errors, or expanding on it. It’s so difficult for me to use closed models with no or summarised thinking now — it feels so painful and gimped.

You don’t know what you’re missing until you’ve seen it. For me it’s almost like going from standard def to HD for the first time.

(This applies to other open models too — Kimi K3 in real world feels below Opus 5 in terms of raw intelligence, but significantly above Opus 5 in usability and personality. And no silly refusals — the model feels like it’s working for me; not working for Anthropic who’s always holding a leash over the model while I pay for it).

I prefer V4 flash, but Luna is ok and included in the OpenAI plan I'm already paying, so... that is the reason I use it.

I gave DeepSeek $50 around june, and I haven't been able to exhaust them yet. The model is super cheap and more than enough for my needs.

I'm my opinion, Flash V4 is less pedantic than OpenAI models, less prone to unsolicited prescriptions and less prone to "helpfully" reinterpreting my instructions (wrongly, of course).

Language distribution shifts. Eventually people will start adopting the distribution used by LLMs, making classification harder.

Also, this doesn't even consider the case where people use LLMs to translate their original works. Or people that use it for spelling/grammar checks.

Personally, I believe these checkers do more harm than good. Any false positive can ruin someones life.

> Eventually people will start adopting the distribution used by LLMs, making classification harder.

I recently heard someone say "that's genuinely the exact solution I was looking for" and had to do a double take.

This will cause cognitive debt anyway. As mentioned in https://arxiv.org/pdf/2509.21972v1: "When students rely on these outputs as a substitute for their own reasoning or critical engagement, the learning process is fundamentally compromised. Genuine learning requires the active construction of meaning, integration of knowledge, and reflective engagement with content. These processes cannot occur through passive consumption of syntactically correct but semantically hollow responses. Without this deeper cognitive work, learners risk mistaking linguistic fluency for understanding, thereby undermining the very goals of education".

Personally, I don't think we will ever be able to reconcile using LLMs and cognitive debt. Even before LLMs we were aware if it: we knew people moving to managerial/PM roles eventually get their coding skills rusted. Well, now we are all in those managerial roles...

Its weird how absolutely desperate we are to avoid humans actually using their brains at any step of the coding process. I don't know if we just need to tell people that its fine to need to think about things, and that its actively healthy to do so. Learning is good for you, and no chatgpt isn't good enough to avoid using your meat

If you don't engage your brain, it'll rot. That's far more important in the long term than a 5% productivity boost or something. I have no idea why you'd trade off your entire technical development and skillset training, for the most short term gains, it doesn't even theoretically make sense if you care about long term productivity

In a way it's not so different from learning in school. There were definitely times I read a textbook for a programming or other CS course and reused some example code or whatever to solve homework problems.

I think the helpful part is taking something that already exists, learning how it works, and rewriting it yourself to internalize it.

Again as usual the more important thing is that you know what you're using otherwise it's just copying.

It is different from before. The programmers are used to read the code of smart or creative people, or the code of knolled people working for years to solve a specific problem, and within this process they analyze and learn to improve, thanks to this self-learning path, eureka moments included. This process includes to search (to read the voice of different perspectives and knowledges, to learn to use critical thinking).

Now is being proposed to read LLMs' slope and unrevised code constructed from statistics as the way to learn? This is a big mistake. IMHO.

Perhaps typing the code by hand means you are more deliberate and less likely to have the LLM produce thousands of lines of diarrhea.

What do you think would be the effect on people that already have the skills and abilities. The LLM would build these systems using the skills that are largely understood by the programmer but piece them in new ways suitable for the system. This could lead to new enmergent behaviors that are not understood by the programmer.

I still think that you can build this model in your head even with LLM's but I'm not sure neither one way or the other.

To repeat their last two sentences:

> Even before LLMs we were aware if it: we knew people moving to managerial/PM roles eventually get their coding skills rusted. Well, now we are all in those managerial roles...

There's always some component of a skill that is not merely knowing something but practising something seemingly procedurally. Even if I understand integration well and have done it thousands of times, if I don't continually practise it from scratch, I begin to forget tiny bits and pieces and that accumulates to an eventually lack of understanding. So it is true for all mental tasks. There really isn't such a thing as understanding something completely without working it out by hand, from scratch. AI exacerbates a lack of understanding in this regard, although admittedly layers of abstraction in the coding realm already do that to some extent...

It's simple enough: If you don't use it, you lose it.

The more you have, the more there is to lose and the longer it may take. But skills and knowledge fade, just as easily as fitness, or a tan.

It's an insidious rule too. Insidious in the sense that you may not realise you're not exercising a skill. You may think that your just doing it slightly differently, but you will adapt. In whatever way you made your life easier, that's where you'll pay, in strength, fluency, depth, whatever.

I don't know how much I agree, I've been in and out coding for different periods of my life.

At each point few days of practice brought me back where I was.

The key is, as you said, practice. I think it's fine to use AI to write code for you, as long as you occasionally force yourself to write code manually. Not only does it help you retain your skills, but it feels more satisfying than prompting, even if arduous.

A few days multiplied by the number of skills I once had translates to well over two months of lost time.

Oh wow, even scammers care about usability and their employees' well-being. What's the excuse for bad UX in internal company software?