Viewing profile — acters

It's sometimes easier to lie than to tell the truth, and being on Linux telling the truth gets me more scrutiny than those pretending to be legit.

I worry that GPT 5.6 will be heavily restricted and have the same feature to fallback to another model like Claude fable 5 does all too often. That fallback shenanigans mess up act…

The biggest loss to them is the right to repair stuff. They will be still making it exceptionally difficult to repair their stuff, and might even dip into exotic materials to make …

I ran it through paddle paddle OCR and it flawlessly did it. Google's OCR through my phone's Google lens had also worked at getting a very good extraction but not 100% correct. Def…

Plus, it is not the bottom I fear, it's the precedent from letting companies slide down the slope. Regulation may try to stop it but history has shown some have slid to the point o…

I've been seeing LLMs act lazy from the very beginning. They got a little better but smaller models really only want to have a single task given to them. Mythos at least does work.…

Would the new upcoming AMD AI ryzen halo desktop be a better value offer? or dgx spark? You would have to get a third party reseller/scalper or refurbished mac mini to get 64gb of …

I am finding Chinese models are introducing more guidelines against cyber. Especially Kimi k2.7 code seems to have extra training against cyber security capabilities. Last one, k2.…

I believe it is because GLM 5.2 has extra anti-cyber training instilled in it. Similar to Kimi k2.7 code. Deepseek v4 pro being in preview with less "safety" training makes it stro…

Which is silly because they seem to struggle with maneuvering around the little plastic tab to have the battery detected as rechargeable.

I am guessing they are trying to make a distinction from mental horny vs physical horny

Yes tokens used (input and sometimes output) are always charged. You likely get charged for the preloaded system prompt, too.

AI consistently places animated objects behind a blur object which causes the browser to constantly repaint. Google's ai mode introduced one, some other websites clearly vibe codes…

They will also prefer subscription or free-to-play than actual offline gaming. This is going to be a disaster

Fascinating, kimi k2 has good clock too from my limited time being on the site.

When ctf organizers attempt to make a challenge "harder", I find they push the challenge into a more "guessy" state. Instead of proving skill, you basically need to guess some obsc…

Yeah, but we have AI now, we don't need our blog posts to over explain or state what it all means to general audiences. The author name-drops a bunch of CTF events hosted by a vari…

Just look at deepseek V4, this preview model uses only 8 GB for 1M token KV cache(the context). It's insanely efficient already. It's just that most models that are coming out are …

Man can't wait for AI in my brain. And then intelligence will be pay to win.

Instead of telling the LLM that "run"works like a cli, maybe just tell the LLM that "run" will execute sh/bash/zsh/etc scripts?

I have a 1660ti and the cachyos + aur/llama.cpp-cuda package is working fine for me. With about 5.3 GB of usable memory, I find that the 35B model is by far the most capable one th…

I have personally seen a rise of LLMs being too lazy to investigate or do some level of figuring out things on their own and just jump to conclusions and hope you tell them extra i…

I'm partially fascinated by their reliance on this model. I do miss the models before gpt 5. Openai is quietly locking it away into some vault as we just need to accept whatever mo…

If it's alright to be pedantic, anyone with programming knowledge can do the same without these tools. What these offer is tried and tested secure code for client side needs, clear…

So basically the same as censorship because that is the exact same thing blocking ports does.