Top Tweets for #lesswrong
Sharing a thoughtful LessWrong piece by my colleague @darin_tsui on AI as biology’s digital microscope: how mechanistic interpretability can help turn biological AI models from black boxes into tools for discovery:
https://t.co/yJnrKbAfMK
#LessWrong #MechInterp
Current AI models have been built around intelligence but are still not fully value aligned; deception and selfish non-cooperative behaviours in AI Agents can potentially be handled by training or aligning explicitly for values.
#values_alignment #AI_models #lesswrong #Effective_Altruism
Intelligence without values can cause havoc;
Imagine intelligence as a hammer,
which when applied in correct directions builds, otherwise destroys.
In a week I'm flying to Berkeley for a #MachineConsciousness conference (´#MC0001´ by @CIMCAI), then stay a month in a Buddhist retreat there, attending also #LessWrong's LessOnline festival in Lightaven (also the Summer Camp and Manifest after).
Anyone around (even LA and such), if you want me to buy you coffee/lunch/beer, I'm happy to drop by and chat:) happy for any tips also!
@SpencrGreenberg For me the question is more the opposite: What interesting essays are from major media? I'm mostly reading independent authors eg @paulg, @slatestarcodex, @robinhanson, and #Lesswrong and my Anki deck has most insights from there. But there are a few mainstream - see thread.
On @ylecun saying who to listen to about #jobs - he and they / them imho are ALL more wrong than necessary. The less wrong blog folks are #lesswrong than most. That said, I too could be wronger than usual. And excuse my typos. Thank you. This concludes my two-bits-in on a difficult but fascinating topic.
Evidence of triple layer processing in LLMs: hidden thought behind the chain of thought.
#Anthropic #LessWrong
Read more: https://t.co/UXcnTFLRfd
[Intro to AI Alignment] 1. Goal-Directed Reasoning and Why It Matters
#Anthropic #LessWrong #DeepMind
Read more: https://postreads.coBUILD_DATE=2025.11.25/feed-item/44165/click?source=twitter
What drives LLM bail? A small Mech Interp study
#Google #LessWrong #Gemma312B
Read more: https://t.co/Lkr0ndPrXY
-speaking audience:#AIAlignment
#AISafety
#PhilosophyOfMind
#Consciousness
#Qualia
#InvertedQualia
#InstrumentalConvergence
#AIExistentialRisk
#EffectiveAltruism
#LessWrong
#Rationality
#DecisionTheory
#Functionalism
#PhenomenalConsciousness
#Orthogonalism
#AIPhilosophy
#HardProblemOfConsciousness
Broader or adjacent communities:#MachineLearning
#AGI
#xRisk
#Longtermism
#Transhumanism
#Neurophilosophy
#Sentience
#MoralPatienthood
Niche but very on-topic tags:#InnerAlignment
#MesaOptimizer
#ShardTheory
#ValueLearning
#CoherentExtrapolatedVolition
#SufferingRisk
#SRisk
By-hand posts fail #lesswrong moderation twice in a row. No constructive feedback, just “we don’t like llm content” without explanation. Seems like well-kept gardens either die by pacifism or live long enough to become an echochamber. Didn’t expect them being irrationally biased
Mükemmel olmak mümkün değil. Asıl mesele, düne göre daha az yanlış olmak. Hayatındaki küçük hataları bile elediğinde, daha iyiye doğru bir adım daha atmış olursun. #lesswrong
New LessWrong post — https://t.co/deneFWk28b #anthopology #ai #lesswrong #identity #aialignment #blogging #blogpost #aiessay #rationality #memory #aimemory #aiidentity #humanidentity #humanity #humanalignment #identitycoupling #imaginedcommunities #halbwachs #anderson
New LessWrong post (long) "Paper Review: Must Rhodes Fall? Differing responses to contentious monumental public art" https://t.co/JM1mB9LTar #arthistory #dissertation #collectiveidentity #imaginedcommunities #lesswrong
On the Normativity of Debate: A Discussion With Said Achmiz
#LessWrong #GreaterWrong #DataSecretsLox
Read more: https://t.co/5mhYFePkCV
@lesswrong The discourse on agency and goal-directedness on #LessWrong ✵ these days seems worth engaging with
Last Seen Hashtags on Sotwe
Most Popular Users
Elon Musk 
@elonmusk
240.1M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
108.8M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.2M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.5M followers
KATY PERRY
@katyperry
86.8M followers
Taylor Swift
@taylorswift13
80.6M followers
Lady Gaga
@ladygaga
72.1M followers
Kim Kardashian
@kimkardashian
69.4M followers
YouTube
@youtube
68.6M followers
Virat Kohli
@imvkohli
68.5M followers
Bill Gates
@billgates
63.4M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
61M followers
X
@x
60.9M followers
CNN Breaking News
@cnnbrk
59.9M followers