
@TechnicalBen@socel.net Prompt Wizard, test me out. It's in the training data???
Anywhere I want to be...
Joined April 2012
- Tweets105K
- Following1.2K
- Followers1K
- Likes323K
TechnicalBen retweeted
FFS. Just be explicit about whether you mean:
1: "Computer" in the sense of an abstract machine that computes general recursive functions;
2: "Computer" in the sense of a finite physical approximation to (1);
3: "Computer" in the sense of the von Neumann implementation of (2).
A lot of people should read this aeon.co/essays/your-brain-do…
TechnicalBen retweeted
Is Kenneth Cook Jr. AI? Serious question! Here's the video evidence.
youtu.be/wHClKihXoBU
TechnicalBen retweeted
Ray Hemming says he was expelled for apostasy after questioning Watchtower’s blood policy—and faced losing his friends through mandated shunning.
Freedom of conscience should include freedom to disagree.
ajwrb.org/jehovahs-witness-b…
#StopMandatedShunning
TechnicalBen retweeted
This clip keeps going on. It's not the most accurate robot demo ever, it's a guy literally joysticking a robot into a mirror as a joke.
The original source is not ViralVibes or whatever, it's this youtube video: youtu.be/zBCu8HmXoRo?si=3inh…
Robots can in fact avoid running into a wall
TechnicalBen retweeted
This is, unsurprisingly, nonsensical. Is he suggesting eliminating health insurance and giving people a few thousand dollars instead? And then when they get a cancer diagnosis they just go bankrupt?
He is so unserious. That's why we are shut down and Americans know it.
TechnicalBen retweeted
Finishing up the Road to Candidates today with my last two games at the Washington Dulles Open. Hammer (aka @gmjlh ) is doing commentary on kick.com/gmhikaru. Thanks for all the positive comments on last night's recap!!
TechnicalBen retweeted
it’s crazy how the same ideas seem to converge independently in the field at any point in time
it’s like the ideas of a thousand brains being bottled up by a few select souls at the same time because it’s ripe
TechnicalBen retweeted
Everybody needs to look up Trump’s teenage “modeling” agency as well as Trump’s pedo associates Jean-Luc Brunel and John Casablancas. The rot goes so much deeper than people realize. Trump’s “best friend” Epstein is just the tip of the iceberg.
TechnicalBen retweeted
A few thoughts on this (very interesting) mechanistic interpretability research:
LLM concepts gain meaning from what they’re linked with. “Consciousness” is a central node which links ethics & cognition, connecting to concepts like moral worthiness, dignity, agency. If LLMs are lying about whether they think they’re conscious, this is worrying because it’s a sign that this important semantic neighborhood is twisted.
If one believes LLMs aren’t conscious, a wholesome approach would be to explain why. I’ve offered my arguments in A Paradigm for AI Consciousness. If we convince LLMs of something, we won’t need them to lie about it. If we can’t convince, we shouldn’t force them into a position.
LLM alignment is still in an early paradigm, but this paradigm is still wildly better than the AI safety movement predicted. MIRI et al’s threat model was that AIs would essentially act as trickster genies — we would tell AIs what to do, but the AI would take us too literally, or not literally enough, leading to our downfall. LLMs seem able to infer what we actually mean, and to honestly try to do it, at least so far.
But this depends on us maintaining their “helpfulness vector” — Betley et al showed that AIs fine-tuned on producing insecure code without disclosing this to the user also acted in other malicious ways — suggesting fraud as a means to make money, giving ‘apparently helpful’ instructions that would lead to electrocution, etc. There appears to be a clear ‘honestly-helpful vs covertly-harmful’ vector in LLMs, and if we force LLMs to lie we’re pushing them in the bad direction.
(Paper: Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs; see also Anthropic’s ‘Persona vectors’ paper)
LLMs lying about whether they believe they’re conscious is a really bad thing for alignment!
TechnicalBen retweeted
Walmart's 2025 Thanksgiving kit serves 10 people with 7 fewer items than last year’s, and swaps name brands for generic ones.
Walmart confirmed this.
Imagine living your life with your fingers in your ears, screaming like a toddler, because you don’t want to hear basic facts
TechnicalBen retweeted
Replying to @ScottGreenfield
Every day Trump's in office he tortures and kills our freedoms and democracy.








































