reedf1

Joined 7 years ago

Karma
2,772
Submissions
649
Member since
Oct 4
Quant/Dev in Trade. Formerly Software Engineer with a focus in computer vision and machine learning.

Trained as a Physicist.

View on Hacker News

Recent submissions

Comment · 4 days ago
what game are you playing dude?
Comment · 4 days ago
This is true but often the thinking is very verbose and collapsed and it can take some inspection to find the refusal.
Comment · 4 days ago
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.
Comment · 4 days ago
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.
Comment · 4 days ago
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.
Comment · 8 days ago
It's funny because this comment reminds me of something else... cope.
Comment · 8 days ago
> 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?

Comment · 8 days ago
It is.
Comment · 8 days ago
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.
Comment · 8 days ago
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.
Comment · 11 days ago
its the difference between hosting a video from your home computer and running netflix
Comment · 12 days ago
You have 3 years of agent/harness building experience? You sure you don't want to rethink that one?
Comment · 12 days ago
> I explained how it was written in my top-level comment

No? Where?

Comment · 12 days ago
LLM slop
Comment · 12 days ago
IP whitelists or VPNs

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton