Tentacles are obviously the better form factor for essentially every task.
Singapore
Joined December 2012
- Tweets8.1K
- Following2.1K
- Followers70K
- Likes12K
(This is a very useful heuristic.)
xianyangcb.substack.com/p/th…
What I've come to believe is a large portion of the population thinks that simply considering abstract examples about human behavior is a sign of immorality. If you give them a trolley problem, they wonder why you think it's okay to kill people.
6
314
Me and my IDE <3
Can any dune book reader explain why anyone would choose to become a navigator in Dune?
In the world of Dune, navigators are barely human anymore. They spend years immersed in highly concentrated spice gas, causing their bodies to mutate severely until they resemble strange fish-like creatures. So, why would anyone accept such a terrible price?
We all know who this is but I'm choosing to imagine Trump and Altman getting increasingly confused and frustrated at each other on account of the latter's inability to comply with the wife-kissing directive.
18
763
Curious to find out what happens when you give a model the ability to create and apply its own steering vectors and then pick experiences to train on.
Self-steering: github.com/EigenformAI/modul…
Self-training: github.com/EigenformAI/after…
"Delightful."
Nvidia's Huang is asked to brief Congress on reported Chinese spy relationship cnbc.com/2026/11/05/nvidia-j…
1
13
1,122
Can confirm.
We have found a critical safety and alignment issue in recent public and internal models from multiple frontier labs which allows them to be misused in a high-stakes domain. It may also increase the risk of catastrophic misalignment.
We have disclosed it to the labs, and they are investigating and mitigating it. As an independent third-party evaluator, we maintain complete editorial independence and will share our findings publicly in the coming weeks.
3
20
752
Maybe I'm just getting older but it feels like the Situational Awareness blow-up comes round earlier every month.
Llama is really getting into the idea of self-steering.
Left: trying out a "storytelling" vector
Right: reviewing the effects afterwards
github.com/EigenformAI/modul…
Doing the background reading for this I ran into one of the most perfectly pitched editorial clarifications in the history of editorial clarifications.
12
662
(The more ethical approach is to give the models the option to steer themselves, naturally.) github.com/EigenformAI/modul…
I think this is the first time I genuinely, start-to-finish, couldn't tell.
If your AI characters sound fake, the fix is almost always in how you write and DIRECT the dialogue in your prompt.
I recently started on the dialogue-heavy scenes for my AI feature film about Beethoven, and too many of the lines kept coming out wrong.
They’d sound too theatrical, too monotone, or too much like a practice read-through between actors.
(all this despite the fact that Seedance 2.5 is fantastic when it comes to realism.)
So through a whole lot of trial and error, I've found that these 5 things made the biggest impact on the quality of the dialogue delivery in my generations:
1. Paying close attention to the written punctuation used.
2. Breaking long lines into shorter ones, with intentional pauses.
3. Using bodily actions as punctuation (this one gave the biggest improvement BY FAR! In the attached clip, note the sniffles in between Beethoven's lines. That alone made the delivery feel much more natural.)
4. Using "anchor gestures" (he lifts his finger as if to say "one sec")
5. Just split your generations in two (stupid simple, but it really makes a difference.)
So if your characters keep sounding like they're reading from a teleprompter, give this a try!