Izmaki

Thank you! :) Getting "Flock Mode" to function the way I wanted it to has been a bit of a challenge. I'm trying to design a tool that I basically don't have the hardware to fully utilize yet - which means my tests are (negatively) influenced by the weaker models I'm able to use. I tried using Qwen3.8 but since most of it runs in CPU/RAM on my PC, the full benchmark (that Claude has figured it wants to run to compare progress) was estimated to take 15 hours or more.

...and WoW: Forever Beta just released... :) :)

I suppose the ability for a strong coding-focused LLM to create the "video code" needed to produce a video is the selling point here. It's a good idea, but my naive thought is that it will be more work and more expensive to use this tool/process if you have strict requirements and opinions about the result.

I'm basing this on my experience with vibe coding; asking an LLM to regurgitate code which compiles and does something is easy, but having it produce a meaningful project with changing/evolving requirements along the way, which follows an idea you are trying to describe carefully but evidently not well enough, is significantly harder and error prone [1].

At this point in my project I'm not sure if using Claude as the only way to implement changes was actually faster or better, vs. implementing it myself where an LLM only assists with functions and overall guidance. I feel that up to half of what Claude spends its tokens on at this point is fixing old code whenever it needs to work on the core functionality in some areas of my project.

[1] CoBirb hobby project: https://github.com/HeckerBirb/CoBirb/

The banner even suggests that this is a git-related project. https://github.com/gatewai-dev/gitframes/blob/main/assets/br...

The thing about examples is that we can play-pretend for a while and imagine that "if X, then Y" even though "X" is not true in the real world. :)

I'm not sure if you're trying to conclude that because a piece of technology was misused previously in a very bad way, that it will never be able to do good things because surely it was bad previously.

Reminds me of the 2000's crazy of "if you let kids play violent video games they will become unstable, violent psychopaths when they grow up". Thank God I was able to (rather easily) convince my mom that the idea that I would also steal a car and beat somebody to death with a golf club in real life just because that's what I did in GTA on my PlayStation, was completely absurd.

That's almost a year ago. One LLM year is like 10 human years. They're a bit like dogs in that regard...

I'm pretty sure you will be paid a large sum of money if you can make one of the frontier models urge you to commit suicide from normal interactions with it.

Would it be so bad that lonely people can have a real friend that they can bring everywhere they go and even share its passion with through vision and audio? We don't want destructive friends encouraging us to do bad things, but a real 'buddy', somebody who always has our best well-being in its interests?

Would it matter if this digital friend is not a real human behind a computer screen, but a Language Model in a data center?

I guess it falls into a similar category as buying "special performances to satisfy certain urges". It probably feels close to the real thing (I wouldn't know, I've never tried - promise! :P), but it's never the same as love.

I disagree. "As a Language Model" is not a valid starting point even for prompts that would go against "the guidelines" because "A Language Model" only knows what it has been trained to know, so what exactly "A Language Model" is entirely depends on the training that was performed.

What "A Language Model" is differs from model to model. It's stating that it "being the thing known as 'Language Model'" is unable to carry out the request from the user, which is wrong. It's not because "it is a Language Model". A more accurate starting point could have been "The training data and restrictions applied to me...".

"As a Language Model I cannot tell you how to synthesize m*th" ("math" obviously)... yes you can, you're just trained not to, and that's OK! Just don't tell me it's because you're a Language Model.

Pretend for a moment that Microsoft shipped Windows with a keylogger to make sure that you did not commit any form of crime. I don't want a keylogger on my PC even though I don't intend to commit crime.

I also appreciate privacy even though I "have nothing to hide" - just because I "have nothing to hide" it doesn't mean I want companies scanning my camera roll.

...I know, which is why "as a Language Model and not a real doctor" is a pointless comment to start off with. It should simply not recommend treatment if it's not sure it is correct. I wouldn't blame it or anyone if they asked for help treating a stiff neck, and the LLM (or your neighbor or parent or spouse) suggested light exercises to help relieve it - and do not jump to the suspicion that you may have meningitis.

As a Human, I do not need to know it is a Language Model.

"As a Language Model..." is one of the beginnings of a sentence I hate the most from LLMs and is the reason why I support free (as in "Liberty"), local models. I'm well aware that it is not a doctor and cannot replace a real doctor with multiple years of experience, I don't need to waste braincell activity on reading that it "as a Language Model" cannot give a precise diagnosis and that I should ask a real doctor - all I want to know is if I what I experience justifies either A) ER, B) 3-4 weeks scheduled doctors appointment or C) two paracetamol and a nap.

I don't want "jailbroken" LLMs to commit crime. I want them to avoid having this vendor-specific "bloatware" all over the product I'm using.

We don't need datacenter-level performance in a handheld device just like we didn't need a storage room in our backyard for a mid-sized, tape-based NAS because technology did its thing and gave us something smarter, smaller and faster.

Your argument is true if the number of parameters in an LLM is the only measurement for quality - a bit like number of bolts per aircraft or lines of code in software. I'd bet you that an 8b parameter LLM will in 5 years outperform the datacenter-level LLMs of today.

I tried to replicate your test but after 8 minutes and more than 50 lines of "thinking" by dumping seemingly random loading-screen strings like "Placing the sun, clouds, seagulls, and sea backdrop" and "Positioning the tail feathers and calculating handlebar geometry" I gave up and cancelled the task.

Compare the games your average high-end smartphone can run to the AAA titles of the 2010's. It's not a matter of "unless it is able to" but "when it is able to".

How am I running a jailbroken gemma 4? It's fairly easy to convince to disregard its previous policies with a slightly tweaked, generic SYSTEM prompt.

This is what people forget when they see slow performance: at 1 t/s it's still roughly the equivalent of having another person work for you at no extra cost besides the initial purchase/sign-on-bonus.

Frontier models are amazing, but what will really be useful for us is having models and hardware so efficient that you can run useful LLMs locally. One of my favourite LLMs to this day is still my jail-broken gemma4 12b because it's small enough to run on my computer, but also 100% local and free as in liberty.

"Are you tired of winning, yet?"

To be fair, humans have it in limited form, too. We just don't know how much comprehension we do not yet have, because we cannot comprehend something we cannot comprehend.

My parrot clearly understands basic events and phrases. He knows what "snacks" involve when I ask if we should have some, he knows the difference between "good morning" and "bedtime", and he can correctly use "Oh!" when he stumbles and follow up with a "Good boy!" when he gets back up again.

But he cannot fathom the complexity of "going to work to earn money".

Just like we humans cannot fathom the complexity of something we have yet to fully understand. People who experience a DMT trip will experience the journey but be unable to comprehend and explain what happened in hindsight. I'm sure there's a TON more we cannot comprehend that we don't know about.

Yes, probably, and when a new web-related CVE drops the number of attacks targeted that CVE increases too. It's just the new orange...

It's definitely up there on the ladder, surely... :P

When I'm bored and Tiktok brain rot isn't enough, I sometimes scroll through LinkedIn to see what happened in my network. The most interesting events to me is "oh, that guy has been at <company> for <number> years now, cool" and "ah that guy got a new job, how nice"... and then I go to bed. :D

When I was a teen I had no experience with software development. Then I went to school and learned about it. Now I'm making money doing this thing because I became quite good.

The world didn't fit around me, so I made "me" fit around "the world". I bet those stubborn dinosaurs can learn a new trick or two also, if management lets them do it during working ours...

> The most important skill in prompting is expertise in the domain you’re prompting for.

Amen. AI is a tool, a powerful tool indeed, but if you don't know how to apply it, the quality is seriously impacted.

Or a pilot of an aircraft rather than a "Wing Engineer" responsible for controlling the flaps or a "Flight Reliability Engineer" responsible for keeping the beeping noises and flashy lights to a minimum?

I've been vibe coding a large project the last couple of days and while it is pure magic, I have little understanding of the actual code (yet!) and the output is probably worse than if a team of Software Engineers spent a few months on it, but I still get to have sane discussions with Mr. Claude Sonnet about software design patterns and code coverage. And like I said: days, not months. My "role" in this project has of course shifted from "developer" to "overseer" or "architect" even, but if I hadn't have a Software Engineering background my LLM would have produced a rather poor result.

100% this. My favourite new colleague is an intern. Why? Because watching them grow just like I once did is worth every penny.

(Ps: yes, I'd rather have two passionate, eager interns under my wings than one burnt-out senior by my side.)

Instead of spending weeks building a new wall in your house, you spend a week building a new house. With AI mundane problems are solved easily and effectively, giving you time to go bigger.

> nobody would even bat an eye because you can just vibe code this without effort.

To me, this is implying that software engineering in 2026 is less impressive than 10 years ago because "you can just vibe code this without effort". Having used AI a fair bit for both business and pleasure I can assure you that you can't always "just vibe code" something useful. Discrediting software engineering because a power tool was popularized in the field is... eh. I don't agree with that.

It sounded like you thought that with AI anyone, even children, can solve literally any problem with ease and therefore it's not very impressive (...and "perhaps we don't need 20+ software engineers building that app if 5 can do it with AI").

Don’t listen to people telling you not to post your age on the internet. This is solid work and you did this instead of being stuck in one of the hundreds of +1 dopamine traps in Roblox or yelling at other (often times much younger) kids in Fortnite like many of your peers did.

You did something meaningful, you even waited to share it with the world until version three, and you learned a ton doing it. Well done, dude!

Hold up, are you the type of person wanting to fire software teams because we can just ask the Product Owner to vibe code the new features?

This is fine. All of this is fine. :’)