How are you not blocked by banking, shopping, even sometimes google search?

Just change servers. Never had a problem with any of those and I have a VPN on my router covering all devices.

Use Brave search instead, Google search has terrible a privacy policy.

Bank is only reason why I'm turning VPN off, but it's for a few minutes. So not so much tracking.

There are inconveniences, but some protection is better than no protection. Trying to protect your privacy online is not a zero-sum game.

Server side tracking.

Bots wouldn't miss the middle paragraph.

That's amazing. I didn't even realize but it seems I read the first paragraph and the last sentence, concluded "moron" and scrolled down.

It's only because of your comment that I re-read the their post.

Then the creator should have a sign up button, not a fake chatbox.

This dark pattern is reminiscent of those online test sites in the 2000's where you spend 10 minutes filling out some quiz, then get prompted for an email address to see the results.

https://chat.mistral.ai/chat <- let me chat and actually responded without signing up.

MoonshotAI had this fake chat box dark pattern.

So I signed up with Mistral instead.

CC actually prompts Claude about this by default in the ~20k system prompt and instructs it to avoid 300s timeout and to be mindful of the 300s cache expiration.

CC also will also block sleeps longer than eg 300s; the harness handholds the model quite a bit.

>the only open model that can do tasks well and efficiently is Qwen3.7-Max

Qwen3.7-Max is a proprietary, closed weight model.

2 reasons.

First, it's not really "1 bit", actually much closer to 2-bit. IQ1_M is actually 1.75bit and IQ2_XXS is 2.06bit This is from the ./llama-quantize --help with most of the quant types and their size in bpw: https://pastebin.com/bCUqGfeE

And to elaborate on the "dynamic" aspect inconito said in the other comment, if you click on one of the .gguf files in huggingface:

https://huggingface.co/unsloth/GLM-5.2-GGUF/blob/main/UD-IQ1...

There are a lot of Q5_K, Q6_K, etc tensors. Only the routed experts (ffn_gate_exps.weight, ffn_up_exps.weight, ffn_down_exps.weight) are heavily quantized, and it looks like the down_proj is actually iq3_xxs for this model.

Yeah, be sure to put everything in tables and include “best balance” for a mediocre option and “great value” for any completely useless options.

Also make sure the shape of the paragraphs is completely uniform.

Am I the only one who doesn't get angry at LLMs?

From the blog:

>I don’t really get anything useful out of these postmortems (e.g., clues about how to rephrase my instructions)

Unfortunately, an LLM can't actually reflect or advise how you could have improve the prompt. Otherwise we could give them a sample output and say "Generate the prompt that would produce this output.