For a 16k context window using q4_k_s quants with llamacpp it requires around 32GB. You can get away with less using smaller context windows and lower accuracy quants but quality will degrade and each chain of thought requires a few thousand tokens so you will lose previous messages quickly.
If everyone has access to the model it becomes much easier to find obfuscation methods and validate them. It becomes an uphill battle. It's unfortunate but it's an inherent limitation of most safeguards.
With the families’ offer, other Jones creditors would get a total of $100,000 more than they would get if First United American Companies bought Infowars, according to The Onion’s bidding document.
So the Onion's bid was higher over all for the other creditors and Jones is mad that they can't pay his way out of this. The trustee is supposed to do what's in the best interest of the creditors, which includes the families.
Also, having your friend buy your assets back for you out of bankruptcy seems like fraud, but I don't know the specific laws.
If she actually did this the right would start calling her a terrorist and she would lose any chance at winning over any right voters on the fence (who probably didn't have strong opinions on the issue prior).
Every credible wiki has moved away from fandom at this point. All that's left is the abandoned shells of the former wikis they refuse to delete and kids who don't know better.
This is actually pretty smart because it switches the context of the action. Most intermediate users avoid clicking random executables by instinct but this is different enough that it doesn't immediately trigger that association and response.
All signs point to this being a finetune of gpt4o with additional chain of thought steps before the final answer. It has exactly the same pitfalls as the existing model (9.11>9.8 tokenization error, failing simple riddles, being unable to assert that the user is wrong, etc.). It's still a transformer and it's still next token prediction. They hide the thought steps to mask this fact and to prevent others from benefiting from all of the finetuning data they paid for.
For a 16k context window using q4_k_s quants with llamacpp it requires around 32GB. You can get away with less using smaller context windows and lower accuracy quants but quality will degrade and each chain of thought requires a few thousand tokens so you will lose previous messages quickly.