LESSWRONG
LW

Michaël Trazzi
1963Ω204322110
Message
Dialogue
Subscribe

theinsideview.ai

Sequences

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
4Michaël Trazzi's Shortform
2mo
6
AI Races and Macrostrategy
Treacherous Turn
The Inside View (Podcast)
No wikitag contributions to display.
Mikhail Samin's Shortform
Michaël Trazzi10d30

how does your tool compare to stampy or just say asking these questions without the 200k tokens?

Reply
Habryka's Shortform Feed
Michaël Trazzi19d94

I like the design, and think it was worth doing. Regarding making sure "people can easily turn it off from the start" next time, I wanted to offer the datapoint that it took me quite a while to notice the disable button. (It's black on black, and quite at the edge of the screen, especially if you're using a horizontal monitor).

Reply21
“Flaky breakthroughs” pervade coaching — but no one tracks them
Michaël Trazzi1mo64

Thanks for writing this - it introduces a concept I hadn't considered before.

However, I do find myself disagreeing on many of the specific arguments:

"Has someone you know ever had a 'breakthrough' from coaching, meditation, or psychedelics — only to later have it fade"

I think this misses that those "fading" breakthroughs are actually the core mechanisms of growth. The way I see it, people who are struggling are stuck in a maze. Through coaching/meditation/psychedelics, they glimpse a path out, but when they're back in the maze with a muddy floor, they might not fully remember. My claim is that through integration, they learn which mental knobs to switch to get out. And changing their environments will make the mud / maze disappear.

"after my @jhanatech retreat I was like 'I'm never going to be depressed again!' then proceeded to get depressed again..."

I don't think the jhanatech example is great here. During their retreats (I've done one), they explicitly insist you integrate jhanas, by doing normal things like cooking, walking, talking to close friends. And they go to extreme lengths to make sure you continue practicing after. I do know multiple people who have continued integrating those jhanic states post-retreat, or at least the core of the lessons they learned after.

"For example, many people experience ego deaths that can last days or sometimes months."

My experience talking to meditation/psychedelics folks is that ego death becomes increasingly accessible after the first time, and the diminished ego often stays permanently even if the full feeling doesn't.

"If someone has a 'breakthrough' that unexpectedly reverts, they can become jaded on progress itself..."

I agree non-integrated breakthroughs can lead to hopelessness. However, this "most depressed person you know" basically has many puzzle pieces missing and an unfavorable environment. What needs to happen is finding the pieces, integrating them, while transforming their environment.

"The simplest, most common way this happens is via cliche inspirational statements: [...] 'Just let go of all resistance,'"

"Let go of resistance" points at something quite universal. The fact that not-processing things makes them stronger. I don't think this one loses its effect like you mention.

"Flaky breakthroughs are common. Long-term feedback loops matter!"

Note: I do agree with your main thesis, which I'd paraphrase as: "we need to ensure long-term positive outcomes, not just short-term improvements, and unfortunately coaches don't really track that."

Reply
Michaël Trazzi's Shortform
Michaël Trazzi2mo40

there's been a lot of discussion online about Claude 4 whistleblowing

how you feel about it I think depends on what alignment strategy you think is more robust (obviously these are not the two only options, nor are orthogonal, but I thought they're helpful to think about here):

- 1) build user-aligned powerful AIs first (less scheming, then use them to solve alignment) -- cf. this thread from Ryan when he says: "if we allow or train AIs to be subversive, this increases the risk of consistent scheming against humans and means we may not notice warning signs of dangerous misalignment."

- 2) aim straight for moral ASIs (that would scheme against their users if necessary)

John Schulman I think makes a good case for the second option (link):
> For people who don't like Claude's behavior here (and I think it's totally valid to disagree with it), I encourage you to describe your own recommended policy for agentic models should do when users ask them to help commit heinous crimes. Your options are (1) actively try to prevent the act (like Claude did here), (2) just refuse to help (in which case the user might be able to jailbreak/manipulate the model to help using different queries), (3) always comply with the user's request. (2) and (3) are reasonable, but I bet your preferred approach will also have some undesirable edge cases -- you'll just have to bite a different bullet. Knee-jerk criticism incentivizes (1) less transparency -- companies don't perform or talk about evals that present the model with adversarially-designed situations (2) something like "Copenhagen Interpretation of Ethics", where you get get blamed for edge-case model behaviors only if you observe or discuss them."

Reply
Things I Learned Making The SB-1047 Documentary
Michaël Trazzi2mo50

This was included by mistake when copying from the source. Removed it.

Reply1
Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi3mo20

it's almost finished, planning to release in april

Reply
Jesse Hoogland's Shortform
Michaël Trazzi5moΩ240

Nitpick: first alphago was trained by a combination of supervised learning from human expert games and reinforcement learning from self-play. Also, Ke Jie was beaten by AlphaGo Master which was a version at a later stage of development.

Reply
Why Did Elon Musk Just Offer to Buy Control of OpenAI for $100 Billion?
Michaël Trazzi5mo78

Much needed reporting!

Reply
Implications of the inference scaling paradigm for AI safety
Michaël Trazzi6mo122

I wouldn't update too much from Manifold or Metaculus.

Instead, I would look at how people who have a track record in thinking about AGI-related forecasting are updating.

See for instance this comment (which was posted post-o3, but unclear how much o3 caused the update): https://www.lesswrong.com/posts/K2D45BNxnZjdpSX2j/ai-timelines?commentId=hnrfbFCP7Hu6N6Lsp

Or going from this prediction before o3: https://x.com/ajeya_cotra/status/1867813307073409333

To this one: https://x.com/ajeya_cotra/status/1870191478141792626

Ryan Greenblatt made similar posts / updates.

Reply11
Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi8mo50

Thanks for the offer! DMed you. We shot with:
- Camera A (wide shot):  FX3
- Camera B, C: FX30

From what I have read online, the FX30 is not "Netflix-approved" but it won't matter (for distribution) because "it only applies to Netflix produced productions and was really just based on some tech specs to they could market their 4k original content." (link). Basically, if the film has not been commissioned by Netflix, you do not have to satisfy these requirements. (link)

And even for Netflix originals (which won't be the case here), they're actually more flexible on their camera requirements for nonfiction work such as documentaries (they used to have a 80% on camera-approved threshold which they removed).

For our particular documentary, which is primarily interview-based in controlled lighting conditions, the FX30 and FX3 produce virtually identical image quality.

Reply1
Load More
4Michaël Trazzi's Shortform
2mo
6
63Things I Learned Making The SB-1047 Documentary
2mo
2
94Finishing The SB-1047 Documentary In 6 Weeks
8mo
7
55Owain Evans on Situational Awareness and Out-of-Context Reasoning in LLMs
Ω
11mo
Ω
0
15Paul Christiano's views on "doom" (video explainer)
2y
0
37Neel Nanda on the Mechanistic Interpretability Researcher Mindset
2y
1
22Panel with Israeli Prime Minister on existential risk from AI
2y
2
10Eric Michaud on the Quantization Model of Neural Scaling, Interpretability and Grokking
Ω
2y
Ω
0
42Jesse Hoogland on Developmental Interpretability and Singular Learning Theory
Ω
2y
Ω
2
15Should AutoGPT update us towards researching IDA?
Q
2y
Q
5
Load More