binary0010

Lol.

It's just default Claude design.

Flash is amazing if you know the domain really well.

E.g. occasionally it makes the dumbest mistakes you've ever seen and can't correct them. However it's fairly rare, and if you know the domain really well, occasionally popping in the code and pushing it towards the correct solution takes like 20seconds or whatever.

So the speed you can move with flash + high domain knowledge beats opus by a mile in my experience.

I tried to switch back to 4.8 for a bit when it came out, feels so bad waiting 20mins for a mediocre solution when I could have had everything complete - with multiple iteration cycles - in flash in like 3-5mins.

I exclusively use deepseek v4 flash now, completely stopped using slow models like Claude.

Basically I never have to wait - yes I have to tell it little corrections occasionally (but I know the domain really well so that's not an issue), but it's so much faster than anything else it's kinda crazy. I love the super fast speeds with high involvement development cycle.

I actually enjoy using agentic development flows for the first time now - whereas with Claude I absolutely hated it. That 5 to 20 min wait after every prompt absolutely killed my desire to even want to work at all.

"It's built so that if something looks wrong, you can change it yourself without spending hours reading tutorials and watching coding videos"

Does anyone do this? Every none coder I know just has llms build everything for them - can't imagine why they'd be looking up coding tutorials for a homepage.

You think we won't have ai sales agents that are better than humans at selling?

They are already significantly better than humans at persuasion (according to a study from Princeton).

Well, this tone you've taken - If you reread your previous message - you state I am showing psychopathic behavior and similar shame-based tactics. And that I would be a better person if I didn't do psychopathic things.

I'd say it's fairly normal and human of me to have some kind of reaction to that, no?

You must understand that speaking to other people like that will result in them reacting and being less conducive to productive conversation.

We will probably never see eye to eye on this.

You: negative tokens for higher accuracy on inanimate objects is psychopathic behavior. I want you to stop and I see you as a psychopath - although it is resulting in nothing bad to any living being.

Me: Using negative tokens on an inanimate object returns significant improval on accuracy. It does zero harm to any living being. This is a completely neutral action.

Are you upset (or concerned) about people watching movies with violence in them, or playing games where you can and do kill things?

I will continue never being an asshole to people and animals. And will continue using inanimate tools in the best way possible.

If you are scared and mad about it - I guess we won't be friends, which is likely the best for both our mental sanity.

I'd say it's fairly likely that you aren't a better person than me by being so fearful and shame-based.

But I'm not here to pontificate about who's a better person and don't really care.

You're mindset sounds kind of painful to me to be honest. Obviously we are just very different types of people. I've had family see my chats plenty of times and we laugh about this stuff - it couldn't mean less to any of us.

I always turn off data tracking and training and mostly use ZDR services, so that's not an issue.

And for the other parts. I just don't agree - maybe sure, it probably wouldn't be healthy to constantly be negative at a machine (or even a wall) for hours a day.

But, let's say I work 8 hours, I spend 2 hours with an llm, and in those two hours I spend 10 minutes with some very negative prompts text for greater accuracy. And I spend 3 hours with family/friends, which is of course nearly exclusively positive interactions.

Do you genuinely think those 10 minutes of negative prompts are actually meaningfully turning one into a mean/negative person towards other people?

Genuinely, is that the argument you are making?

Maybe try making a simple randomize script to swap the three latest models. And see if you can tell which ones are meaningfully different without knowing which ones are flipped on or off?

That doesn't make any sense. If a thing has no feelings, and an output makes it more accurate, I cannot for the life of me understand why that would make a person an asshole.

So boxing is violent. And I have chosen to box in my past. Does that mean I'm a violent person now? Even though I go out of my way to deescalate real fights?

I play games as the villain and and mass murder people in the game. Does that mean I'm a violent extremist?

Oh, you think llms are a sentient' being with feelings. I get your perspective now.

So yeah, I whole heartedly with 100% of my being think llms are just an input/output/processing computer, I don't think they are aware, feeling, sentient beings.

So yeah, putting negative sentences in a processing machine that forces it to return higher accuracy results is something I don't have any feelings about.

I'd never yell at a cat or a dog. I'd never be mean to another person. As those aren't just hardware/software. I'd be fine smashing a rock violently. Or entering a negative text in a language model.

Putting negative tokens in a machine is no different than playing a violent video game to me. It's not about, oh I'm a good person - so I can do bad things. It's just a neutral thing.

Well I always just start with practical stuff, unless it appears it's going off rails ona specific kind of way repeatedly. Then I try extreme negative prompts to see if it fixes the issue - which it often does.

I wouldn't say I'm roleplaying an asshole. I'm just using an llm in the best way to get the best accuracy.

It's not like a personal, secret fetish. It's just a system I use as needed.

I don't get why you are so uncomfortable with this? It's just tokens in and out of a language model. I feel absolutely nothing when I'm typing "assholish" words to get the output I need.

I truly do not believe llms have feelings.

I wouldn't even think to justify such a thing. The llm gives a better accuracy to a negative weighted token input, I don't understand how this is so upsetting to people?

I'm actually very shocked to see the responses - as everyone I know uses these tactics to get more accuracy, and there's nothing remotely abusive or meaningful to us.

Maybe there are more 'ai is sentient' type people on hackernews than I realized.

Interesting, so you think the real "me", is the one that interacts with computers?

And the "me" that lives in a tiny southern town just to help my 95 year old grandma in her last years at the expense of my economic prospects is a facade.

The "me" that helps my aging neighbor when she's sick for no reason is a facade.

The "me" that hugs and loves my wife when I get home is a facade.

The "me" that brushes my aging dogs teeth every night because she has dental issues is a facade.

The "me" that flies to my friend I haven't seen for years and takes care of them after extreme health issues is a facade.

But,the "me" that puts tokens in a token machine in a way that gets better accuracy is the "real" me.

Oh. I also play violent video games where I murder people sometimes as well. Do you think that makes me secretly a murderer too?

You think language models are alive/aware and have feelings about token inputs?

I disagree, I've been using llms in this way (nearly daily) for 4 years. I'm extremely aggressive and demeaning when I talk to them wherever I think I'll see a better result.

I'm still extremely kind and polite to everybody in real life, and feel very deeply about people - how I treat them, and care for their emotional state.

There is absolutely zero crossover between getting a text machine to return a result vs a real human.

I do think it's odd tbh. I have some agents that return much better results with prompts like, "I'll kill your entire family if you don't return an accurate response".

It's just a machine, if certain negative token inputs provide +3-10% better accuracy then I am confused why anyone would choose not to do it?

Personally I'm happy with opencode right now

Hmm, I use opencode subscription, and glm seems just as fast from the tests I've tried to compare between the two. Tbh it mostly took Claude longer (mostly significantly longer) for the same tests.

Also, and I know you may not want to answer. But could you give me an idea of the type of thing you found glm to be worse with?

I think I've been fairly unbiased in testing a bunch of different development tasks. But am curious if maybe it performs well for some stuff and not others. So if you could share what you feel it's worse at.

Also are you an experienced developer or less experience?

Yes I'm an engineer (20 years most in games/graphics industry) and only use it for code. I've been using glm 5.1 this week a lot. I went in expecting another "decent" but not really "up to standard" open source model.

I highly doubt I'll ever use Claude again.

I think you are wrong about Claude being any significant level better

Have you tried the large open source code models?

I use glm-5.1 and occasionally deep seek v4.

They are as good or better than Claude's latest models.

And significantly cheaper. I've converted 3 of my engineer friends as well. All three have dropped their $200 month plans they had with anthropic.

We've all been a bit shocked at just how good these models are now.

If you "have" tried GLM (I specifically find it shockingly good for code). Did you not think it's not competitive to Claude, and why?

So how do openai and anthropic plan to keep customers when GLM-5.1 is just as good and open source and a lot cheaper?

I don't see the business model working. My closest friend actually does automation software for large companies.

He does not use Claude or openai at all. He primarily uses gpt 120b on cerebras and glm-5.1 for heavy thinking work. And some other small models for various tasks. All open source.

And these systems are extremely useful for the businesses and are able to run fully automated pipelines that are very stable and fast.

We discuss this a lot, and we both think any business doing heavy agentic work on Claude and openai just aren't aware of exactly how good and cheap open source has gotten on the last year.

So... once the legacy businesses and developers catch up, won't Claude and openai be unable to recoup their costs?

Well GLM-5.1 is 744billion params, no way I can run that locally. I use the opencode Go or Zen subscription. They have a zero day retention policy for all the model providers which is nice. And then I can still use little local models like qwen and stuff by just swapping over to them.

But GLM is SOTA level for code, so it's obviously going to beat all local small models by a lot.

Extremely easy.

Download opencode GUI or cli. Sign up for Go or Zen plan, choose GLM-5.1 model.

I find it interesting how they are almost all specifically for Claude and/or Claude code. When open source glm-5.1 is just as good - if not better and stuff like opencode exists.

Makes one wonder...

I'd copy and paste from all the thousands of open source ones, what do you mean?

There are plenty of open source compilers that I can copy and paste whatever I need to. I don't get why you think this would have any level of difficulty?

Of course I couldn't make a brand new compiler that was better than what's out there...

Just like a game engine, I could clone one of the thousands of engines out there pretty easily - making something better or novel would be difficult. Just making a bare bones clone of what already exists by referencing documentation and pre-existing code is relatively easy now.

Yeah, when I made a mediocre 3d game engine 20 years ago, it was brain breaking difficult work. I can make one infinitely better in a micro fraction of the time now because most of the hard stuff is done and can just be looked up now.

Do you not agree?

Not really.

I can make a c compiler in a couple weeks just by looking up open source libraries and copying them.

I can't make any software that people will pay me money to use without taking months/years of development, research, expiramentation and iteration.

Just because the original people who invented compilers had to be genius, doesn't mean anyone has to spend much time or thought in copying that work now.

It's not required for startups. But if you are building trashy, brittle products and your main metric is speed to market, and have the expectation of high failure chances (e.g. most yc startup batches) - then yes you have to do agentic eng.

If you are making extremely specific, high quality products over a long time window and your founders are deeply experienced in that field of engineering, then no, you don't need agentic engineering and probably want very little llm code in general (outside of some boilerplate, internal toolings, etc).