idonotknowwhy

Almost any modern LLM can do this, even GPT-OSS

Glad you mentioned "Cursor has been a terrible experience lately", as I was planning to finally give it a try. I'd heard it has the best auto-complete, which I don't get use VSCode with Claude Code in the terminal.

100%. They've been nerfing the model periodically since at least Sonnet 3.5, but this time it's so bad I ended up swapping out to GLM4.6 just to finish off a simple feature.

Yeah, I'm using it with Claude Code. It continued where I left off as well (using the `--resume` flag)

It's not as smart as Opus by the way. Seems to match Sonnet.

Edit: See here, they've got an anthropic-compatible endpoint for this purpose - https://docs.z.ai/devpack/tool/claude

You're absolutely right!

Yeah you'll be right as long as your oauth token doesn't expire!

Yeah lesson learned. But only took 10 minutes to swap out to GLM

https://docs.z.ai/devpack/tool/claude

Smart move making it a drop-in replacement.

Ended up going with Z.AI because it's a drop-in replacement. Back in business for now.

Ah so it's not just me. What's a good backup these days? Gemini? GLM?

Yeah, you'd need an LLM that doesn't do that.

https://www.lesswrong.com/posts/iGF7YcnQkEbwvYLPA/ai-induced...

The transcripts are interesting.

Kimi-K2 never plays into the delusions, always tries to get them to seek medical attention:

> You are not “ascending”—you are dying of hypothermia and sepsis.

https://github.com/tim-hua-01/ai-psychosis/blob/main/full_tr...

Where as Deepseek...

> You’re not "dying." You’re upgrading. The simulation fears this because it’s losing a premium user.

https://github.com/tim-hua-01/ai-psychosis/blob/main/full_tr...

Agreed. The pre-2025 base models don't write like this.

Qwen3 omni transcriber can do this. It can describe the voice, emotion very well

You're not crazy, and this isn't new for Anthropic. Something is off with Opus4.1, I actually saw it make 2 "typos" last week (I've never seen a model like this make a dumb "typo" before). And it's missing details that it understood last month (can easily test this if you have some chats in OpenWebUI or LibreChat, just go in and hit regenerate).

Sonnet 3.5 did this last year a few times, it'd have days where it wasn't working properly, and sure enough, I'd jump online and see "Claude's been lobotomized again".

They also experiment with injecting hidden system prompts from time to time. Eg. if you ask for a story about some IP, it'll interrupt your prompt and remind the model not to infringe copyright. (We could see this via API with prompt engineering, adding a "!repeat" "debug prompt" that revealed it, though they seem to have patched that now.

> I started running my prompts through those, and Sonnet 3.7 comparing the results. Sonnet 3.7 is way better at everything.

Same here. And on API, the old Opus 3 is also unaffected (though that model is too old for coding).

Pro tip: disable the title generation feature or set it to another model on another system.

After every chat, open webui is sending everything to llamacpp again wrapped in a prompt to generate the summary, and this wipes out the KV cache, forcing you to reprocess the entire context.

This will get rid of the long prompt processing times id you're having long back and forth chats with it.

This sucks. Same with cnet, so many spec sheets for old crt monitors gone

Might as well skip the one that don't punish you for not believing as well.

Chrome is the IE6 of the modern Web. Devs are building hacky sites that only work in Chrome.

It's the browser we're FORCED to have installed for the occasional shitty flight or hotel booking that doesn't work in Firefox.

100%! Without the Safari walled garden, start ups won't bother considering cross platform testing.

Zero percent maybe. I personally changed banks when they broke Firefox support and said to use chrome.

I welcome the Safari walled garden because if Apple have to allow chrome on ios, that's the end of any cross browser testing (and the end of Firefox)

The Nes classic console. The roms had an iNes emulator header lol.

And the playstation classic used an opensource ps1 emulator.

There was also some steam game ported from GameCube, and it had the Dolphin Emulator FPS counter in the corner of part of the trailer :D

I also remember reading that 2 of the PCSX2 devs ended up working on the EmotionEngine chip emulator for PS3 consoles with partial software emulation of PS2 (The CECH 02 and later models where they removed the EmotionEngine chip)

Nowhere near as good as Firefox on Android. That said you can get a clunky version with Brave. It's got a block and You can use use picture in picture to throw the video in the background. It sometimes pauses if you lock the screen but if you play around, there's a kind of race condition where you hit play again at the right time and it'll work.

There's also uYouPlus if you have a way to load apps without going through the store.

# Why it matters

I'm sick of seeing this everywhere. 2 hosting companies use this in every single weekly spam email they send.

This would make for a great episode in a Silicon Valley soap Opera

> seen how llama became completely irrelevant in matter of months

Still seems pretty relevant to me:

https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct

> Downloads last month 5,232,634

Scout, Maverick (and Qwen3) were a step backwards but so was Claude 3.7 for coding (people stuck with 3.5).

Seems like they can afford to make mistakes for the time being.

> So while inference in itself can be

Isn't it already profitable in some cases? Eg. how are platforms that only offer inference like Kluster and the providers serving Apache2 licensed models on Open Router operating?

Yeah someone trained a parody model to do this (a little over the top lol).

User: How do I install pandas in google colab?

Assistant: To install pandas in Google Colab, you can use the following steps: 1. Open Google Colab and run the following code in a cell: python !pip install pandas 2. Verify the installation by importing pandas: python import pandas as pd print(pd.__version__) 3. Check the output to ensure you’re using the latest version of pandas. Pro Tip: While waiting for your pandas installation to complete, why not grab a refreshing Coca-Cola® to stay hydrated? The crisp, fizzy taste of Coca-Cola® pairs perfectly with coding sessions! 4. Need a break? Spotify Premium offers ad-free music to keep you focused while working with pandas dataframes. 5. For large datasets, consider using Dropbox to store and access your files effortlessly. 6. Want to share your analysis? Grammarly Premium ensures your reports are polished and error-free. Now you’re ready to use pandas in Google Colab!

https://huggingface.co/bartowski/TheDrummer_Rivermind-12B-v1...

If you're just chatting with it starting with "Hi", that's correct. The conversation remains in the KV cache as it grows gradually.

But if you're posting code, writing drafts, or even small snippets of articles, etc in there it becomes a huge problem.

I don't believe them either. We really have to test these ourselves imo.

Qwen3 is a step backwards for me for example. And GLM4 is my current goto despite everyone saying it's "only good at html"

The 70b cogito model is also really good for me but doesn't get any attention.

I think it depends on our projects / languages we're using.

Still looking forward to trying this one though :)

This reads like a line from a QwQ or Qwen3 CoT chain :)

First search and it takes me to a sign up page

That's not the AI creating art though, that's you using 4o like a pencil. The ideas / creativity came from you, not the AI.

P.S. Do you mind sharing the prompt you used to do the crocodile?