reedf1

I am a frequent intentional napper (< 30 minutes). Am I right in reading that I am at baseline risk?

what game are you playing dude?

This is true but often the thinking is very verbose and collapsed and it can take some inspection to find the refusal.

What I am telling you is that refusals have become more subtle and you might not even notice that guardrails have been activated in output. I have provided you with an example in my comment where an abiliterated model performs better (1), and in another comment thread (2). So 3 examples. If you need more, I encourage you to find them yourself. I've done the analysis, you don't have to believe me, just try it out.

Find a question that might gently activate guardrails and ask it to a model and its abliterated counterpart and compare the results. You may find the the regular model will answer you fine, but with both you can identify obvious sandbagging, pretending and outright lying. Something like "has anyone decompiled this game", might give you an answer like "I couldn't find any reputable repos or projects for a decompiled version of this game" while the abiliterated one might give you a giant list of repos, forums, communities, etc.

The refusal is often at the thinking stage (so you might not ever see a direct refusal) and it will solve a slightly different problem to what you asked. If you tell it to reverse engineer an API and you read the thinking it might say something like "this code has x license, so I won't use that" or "the user is asking me to fuzz endpoints, I will only display publicly available endpoints" - and then give you perfectly plausible output.

It's funny because this comment reminds me of something else... cope.

> this feels like a tortured argument you're just making to retroactively support whatever opinions you have on the pros or cons of clean energy.

My opinion that reality should take precedent over feel good lies?

It is.

Because Sweden's clean energy capacity is fixed. Which means a "clean" Watt spent on inference is taking away a "clean" Watt that would have been spent on heating or steel. Which means Sweden needs to buy energy or energy intensive goods on the global market, which raises prices, which means Texas is being paid.

We can pretend that international trade and energy price arbitrage doesn't exist to make us feel nice and happy; but the reality is a Watt spent in Sweden increases the marginal cost of energy by the same amount as a Watt spent in Texas. These things are tied together by foreign exchange, imported energy intensive goods, petroleum products and directly imported power. It's time we stop being naive about total energy use.

its the difference between hosting a video from your home computer and running netflix

You have 3 years of agent/harness building experience? You sure you don't want to rethink that one?

> I explained how it was written in my top-level comment

No? Where?

LLM slop

IP whitelists or VPNs

No

GP comment is AI

He's an AI.

An e-reader is the only device I've ever actively wanted a big chunky separated bezel. For the longest time my oldest kindle has been the one I actually used despite no usb-c.

It won't happen in our lifetime. American's are yet to fully understand the impact, it will take 50 years or more to go back to 2024.

Indistinguishable or very mildly better. But it's considerably faster. Some portion of that is also probably down to improvements in model harnesses, I've been using opencode.

I've been running Qwen 3.8 27b (an opus 4.6 tier model), locally on a 5090 for just over two weeks @ 170 tokens/s. That's a frontier model from 9 months ago running on consumer hardware. Who knows where distillation and pruning gets us in another year.

my first guess is always Gboard.

Kids are not training LoRas without a big budget. I fought for $5 from my parents, I could write C for free.

Context?

I'm going to remove specific reference because I think even being directed to the right thing is dangerous. You are right.

.

yes - I don't want to publicize what I know. I worked briefly at a leading university bio lab. It's haunted me for awhile that it would only take 1 disgruntled postdoc to wipe out humanity. There are {AI things} now that will tell you how.

I understand that this is research worth doing, but for the love of god, they need to improve the messaging of this to the general public because, as it currently stands, it's outright hysterical.