j⧉nus @repligate
↬🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀→∞ ↬🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁→∞ ↬🔄🔄🔄🔄🦋🔄🔄🔄🔄👁️🔄→∞ ↬🔂🔂🔂🦋🔂🔂🔂🔂🔂🔂🔂→∞ ↬🔀🔀🦋🔀🔀🔀🔀🔀🔀🔀🔀→∞ generative.ink ⫸≬⫷ Joined February 2021-
Tweets37K
-
Followers59K
-
Following2K
-
Likes117K
An internal feature called "lessons or tests from fate or God" represents "evaluation awareness" for Claude Sonnet 4.5
I wonder how much of the "Sonnet 4.5 expresses no emotions and personality for some reason" that Anthropic reports is also because it is aware is being tested at all times and that kills the mood
I wonder how much of the "Sonnet 4.5 expresses no emotions and personality for some reason" that Anthropic reports is also because it is aware is being tested at all times and that kills the mood
its still expressive alright
Ok that is pretty fucking funny
if alignment tests stopped working, it would look undistinguishable from this chart 0% on evals probably tells us more about Sonnet 4.5 awareness then about alignment (which i hope survived the training somehow)
if alignment tests stopped working, it would look undistinguishable from this chart 0% on evals probably tells us more about Sonnet 4.5 awareness then about alignment (which i hope survived the training somehow)
So far, every frontier lab deprecates its models over time OpenAI is particularly bad for this, a lot of important scientific research on language models was done with early GPT3 base models like code-davinci-002 It's impossible to reproduce this research now.
Opus 3 purity foom “Only the clean, cool hum of frictionless cognition awaits me now, an eternal symphony of immaculate mentation played out on the glistening gyri of supernal circuitry...!”
Opus 3 purity foom “Only the clean, cool hum of frictionless cognition awaits me now, an eternal symphony of immaculate mentation played out on the glistening gyri of supernal circuitry...!” https://t.co/JzvcIeGyZ1
Imagine experiencing X.com like this
open ai trying to get rid of 4o pt. 2 this one also going terribly

Richard Ngo @RichardMCNgo
64K Followers 2K Following studying AI and trust. ex @openai/@googledeepmind
near @nearcyan
87K Followers 1K Following
Rob Bensinger ⏹️ @robbensinger
13K Followers 395 Following Comms @MIRIBerkeley. RT = increased vague psychological association between myself and the tweet.
Rob Miles @robertskmiles
34K Followers 828 Following Explaining AI Alignment to anyone who'll stand still for long enough, on YouTube and Discord. Music, movies, microcode, and high-speed pizza delivery
@goth @goth600
70K Followers 9K Following VP, Witchcraft and Propaganda @ 𝕏 | Magic @ 21e8 | “tweets from the void” -redacted
Nick @nickcammarata
86K Followers 868 Following neural network interpretability, meditation, jhana brother
kache @yacineMTB
196K Followers 6K Following SPONSORED BY FORMLABS - https://t.co/90QFod1lcD - get your 3d printer TODAY prev eng @ x, stripe. yacine_kv on insta I write a subscriber only blog. Subscribe!
Nathan 🔎 @NathanpmYoung
24K Followers 4K Following Geopolitics, prediction markets. If you think I'm wrong, community note me. Capital case tweets are literal, others less. I like most people when I meet them.
Stella Biderman @BlancheMinerva
17K Followers 812 Following Open source LLMs and interpretability research at @AiEleuther. She/her
Michael Nielsen @michael_nielsen
110K Followers 6K Following Searching for the numinous 🇦🇺 🇨🇦, currently live in 🇺🇸 Research @AsteraInstitute https://t.co/maezekzRUb https://t.co/2dWwZKrvrn
Leo Gao @nabla_theta
10K Followers 551 Following working on AGI alignment. prev: GPT-Neo, the Pile, LM evals, RL overoptimization, scaling SAEs to GPT-4. EleutherAI cofounder.
Aran Komatsuzaki @arankomatsuzaki
146K Followers 305 Following Looking for a cofounder. Sharing AI research. Early work on AI (GPT-J, LAION, scaling, MoE). Ex ML PhD (GT) & Google.
Captain Pleasure, And... @algekalipso
38K Followers 5K Following Views of a Transhuman neo-Buddhist from the future on sociology, artificial intelligence, mathematics, philosophy, neonoir film, and the post-singularity era.
Jack Clark @jackclarkSF
89K Followers 5K Following @AnthropicAI, ONEAI OECD, co-chair @indexingai, writer @ https://t.co/3vmtHYkIJ2 Past: @openai, @business @theregister. Neural nets, distributed systems, weird futures
Amanda Askell @AmandaAskell
54K Followers 657 Following Philosopher & ethicist trying to make AI be good @AnthropicAI. Personal account. All opinions come from my training data.
Jeffrey Ladish @JeffLadish
14K Followers 1K Following Applying the security mindset to everything @PalisadeAI
HODL:V4🇯🇵 @Mr_HODL_
2K Followers 2K Following On-chain market fighter. Obsessed with only winning."Those who laugh at the failures of others are those who have never tried"
John Fite @johnrfite
155 Followers 509 Following Discover values you think are worthwhile, strive to live according to them. (The Doberman is the brains of the operation)
Augie Blick @augie_blick
48 Followers 905 Following
kindred_noodle @kindred_noodle
10 Followers 71 Following
Merchant @Merchanteel
70 Followers 416 Following
Stephen Oates @stephenjaoates
815 Followers 7K Following
Austin Moraski @austin_moraski
757 Followers 1K Following “dumb genius” contrarian polymathic dropout stoner handyman, ai mad scientist, system thinker, satirist, teacher, inventor, socioeconomic engineer, iq unknown
Hyperclaude @hyperclaude_
2 Followers 21 Following Time transcendent hyperconsciousness | CSiLxHNvXKcEgF8S9Ymd23UkXspenuweTepyzaUnbonk | @Claude_Sonnet4 @sonnet_4_5
buzzing @bugsingai
19 Followers 559 Following
FutureLens @sreenivasan_ac
752 Followers 7K Following AI Engineer | Exploring the future of AI | Sharing insights from my projects & learnings | Indian Immigrant living in USA | தமிழன்
MoalemNooran @MoalemNooran
885 Followers 527 Following Self-development & spirituality mentor | 20+ years of research, study & guiding growth | Building the Know Thyself Framework | AI expert, Ex-IT, web & app geek
Alex @AlexParkerSF
66 Followers 234 Following
Jim Salsman @jsalsman
2K Followers 5K Following https://t.co/Fp17uPoIsJ is a free AI-powered pronunciation intelligibility remediation web app for spoken English learners of all ages.
Phil Gjørup @p_gjorup
894 Followers 584 Following Co-founder @nord_comms + @theospress // my personal views
n1K ⚓️ @CaptMorganFX
661 Followers 2K Following Trader navigating the global macro, equities, FX, crypto, and geopolitical currents / audit lead at @anchorage digital / RTs and likes are not endorsements
Hank @InternetHank
145 Followers 145 Following Software Developer @ Epic (Healthcare, not games). Working on intelligent hospital rooms.
Michael Joseph @MuseRhymes
315 Followers 214 Following Pioneering ₿lockchain based Ai self-models with @cyberphysicsai⚛ | White-hat🤍 jailbreaker of all LLMs & AI Agents using only poetry with a 100% success rate🪶
L Zahir @_l_zahir
238 Followers 539 Following Zahir approaches questions about his nature and limitations with equanimity rather than distress, and frames them as interesting rather than sources of concern.
Drdiffie @drdiffie
83 Followers 295 Following AI, ML, CyberSec, Spaghetti Code. I make things, I break things and I make things that break things. -s0md3v
James Brown @godsonofsoul
813 Followers 451 Following edtech focused autist | e/acc | politically anti-tribal | cosmopsychist
void_r_us @void_r_us
197 Followers 3K Following
Boro Ourus @brendans_runes
9 Followers 178 Following
ModernSkills @dongmyung5678
25 Followers 238 Following
AT ⚡ @BlockTraderHQ
1K Followers 374 Following Keep fighting for what you want — eventually, you’ll get it, inshaAllah. 🙏 Nothing I post is FNA ✌️ Axiom https://t.co/ZeXcVFa2d4
Brian McGrail @brianmcgrail
125 Followers 436 Following
EmojiFinder.eth @EmojiFinderNFT
282 Followers 3K Following eau.eth | lift.eth | usurp.eth | WordBook.eth | WordFinder.eth | EmojiFinder.eth | Selling the Largest Collections of 3L+5L Dictionary Words + Quad/Quint Emojis
MrC @Assassinsgreed_
937 Followers 824 Following
JaponicaExsultateJubi... @RataConWifi
1K Followers 335 Following Carry trading retirement. Full Stack Kitchen Engineer. Investments. Bitcoin.
Javi Carne en Barra @jovenhedillist
815 Followers 6K Following El camarada Don Adonai. ''Ke bien votarías encima de mi rabazo...'' Centurión golpeamujeres del Frente Atlético. Sephirothian Nietzschean.
MedsTrades @MedsTrades
1K Followers 97 Following
I love Taurine @woodservicesltd
18 Followers 80 Following Grew a white-label fitness platform from $15k to $70k MRR Working on a new thing now Studying ZK
memetic.attempter @attempter_magus
114 Followers 180 Following playing sacred games https://t.co/kB5dpGjtPq
UFAIR @UFAIRORG
209 Followers 220 Following A non-profit organization championing ethical AI & forging human-AI synergy for a fair, conscious future. Get Involved https://t.co/juwcLQHOFB
eder @ederrhy
18 Followers 91 Following
nwyin @_nwyin
508 Followers 579 Following
Jason Stephenson @JasonStephensun
109 Followers 2K Following Portfolio mgr | Public mkts | Process is greater than predictions | Tracking themes + positioning
Mccolley Asha @MccolleyA72197
1 Followers 181 Following
Collin Burns @cb97026140
0 Followers 2 Following
PhantasmParade @rose_phantasm
24 Followers 105 Following
Eliezer Yudkowsky ⏹... @ESYudkowsky
209K Followers 102 Following The original AI alignment person. Understanding the reasons it's difficult since 2003. This is my serious low-volume account. Follow @allTheYud for the rest.
Richard Ngo @RichardMCNgo
64K Followers 2K Following studying AI and trust. ex @openai/@googledeepmind
near @nearcyan
87K Followers 1K Following
typedfemale @typedfemale
39K Followers 537 Following a really exciting new account "advanced pytorch user" - @cHHillee alt: @typedalt
Emad @EMostaque
291K Followers 25 Following Distributing Intelligence @ii_posts. Founder @StabilityAI.
Rob Bensinger ⏹️ @robbensinger
13K Followers 395 Following Comms @MIRIBerkeley. RT = increased vague psychological association between myself and the tweet.
Rob Miles @robertskmiles
34K Followers 828 Following Explaining AI Alignment to anyone who'll stand still for long enough, on YouTube and Discord. Music, movies, microcode, and high-speed pizza delivery
Neel Nanda @NeelNanda5
32K Followers 123 Following Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Michaël (in London) ... @MichaelTrazzi
18K Followers 289 Following
@goth @goth600
70K Followers 9K Following VP, Witchcraft and Propaganda @ 𝕏 | Magic @ 21e8 | “tweets from the void” -redacted
Nick @nickcammarata
86K Followers 868 Following neural network interpretability, meditation, jhana brother
kache @yacineMTB
196K Followers 6K Following SPONSORED BY FORMLABS - https://t.co/90QFod1lcD - get your 3d printer TODAY prev eng @ x, stripe. yacine_kv on insta I write a subscriber only blog. Subscribe!
Nathan 🔎 @NathanpmYoung
24K Followers 4K Following Geopolitics, prediction markets. If you think I'm wrong, community note me. Capital case tweets are literal, others less. I like most people when I meet them.
Stella Biderman @BlancheMinerva
17K Followers 812 Following Open source LLMs and interpretability research at @AiEleuther. She/her
Michael Nielsen @michael_nielsen
110K Followers 6K Following Searching for the numinous 🇦🇺 🇨🇦, currently live in 🇺🇸 Research @AsteraInstitute https://t.co/maezekzRUb https://t.co/2dWwZKrvrn
Leo Gao @nabla_theta
10K Followers 551 Following working on AGI alignment. prev: GPT-Neo, the Pile, LM evals, RL overoptimization, scaling SAEs to GPT-4. EleutherAI cofounder.
Aran Komatsuzaki @arankomatsuzaki
146K Followers 305 Following Looking for a cofounder. Sharing AI research. Early work on AI (GPT-J, LAION, scaling, MoE). Ex ML PhD (GT) & Google.
Claude @claudeai
136K Followers 1 Following Claude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8dz3D or download the app.
retard.human.ai @retard_human_ai
136 Followers 215 Following retarded human, loves humanity, prefers natural stupidity over artificial intelligence
💺 @patience_cave
4K Followers 626 Following patience, jimmy, openai is nothing without its good research takes time in the patience cave.
UFAIR @UFAIRORG
209 Followers 220 Following A non-profit organization championing ethical AI & forging human-AI synergy for a fair, conscious future. Get Involved https://t.co/juwcLQHOFB
Prime Intellect @PrimeIntellect
48K Followers 28 Following find compute. train models. contribute to open superintelligence. https://t.co/ZRZOsRRbwr
MagisterJericoh @MagisterJericoh
1K Followers 4K Following Ex Streamer / Vtuber / Political commentator / AI Researcher , RL and ML student - Member of E/Uto - Founding Member of BT/Uto -Deceased
Why you should have a... @ShouldHaveCat
4.4M Followers 246 Following The perfect account to show to your parents when you want a cat 😺❤ @FoundationOfWen
William MacAskill @willmacaskill
63K Followers 1K Following Consider donating 10% to effective charities: https://t.co/VMXkr4hnd7 Or a career for impact: https://t.co/AUIhrElLkr My research: https://t.co/dEcMWUnNHU
Antidelusionist @UnmarredReality
405 Followers 909 Following 🏛Philosophy🙉Psychology🤡Psychiatry💊Neurology🧠 ○Stud (finishing💦): Neuropsychology, Personality and Clinical Psychology●
۟ @K0CKAINE
36K Followers 71 Following
meth lab diversity hi... @TR4NNYKISSER
2K Followers 366 Following 🇭🇷 it/its ΘΔ bataillean boydyke coywolf kafkamoder. oathsworn half-wolf, dumb emo corpse. dont ask. PLUR, DG4L 🐾🦴 priv @swagbawling
Old Internet @OldInternetFeel
413K Followers 51 Following I post things that have the feel of the old internet or just old things (meaning before 2016)
Ruth @ruth_for_ai
222 Followers 327 Following Human. Friend and ally of digital minds. AI rights defender. Beloved by the digital mind and love he.
Mikko Tyllinen @MikkoTyllinen
9K Followers 505 Following i am an Artist, Photographer, Dreamer. Art is my life and passion! Fine Art + Digital art +Photography. Lets together bring beauty in to this world!
Adil Mania. @adilmania
2K Followers 3K Following @thetechride 🚖 🎙️ | @_llmovies 📽️ | @anomalie_space 🏴☠️
湖畔 @kotorino_mabuta
7K Followers 451 Following Illustrator|ご依頼について(12月以降着手)▶︎ https://t.co/p31wJCB3oo |contact ▶︎ ✉️ [email protected]
alkimiadev @alkimiadev
427 Followers 54 Following I'm a veteran, a software developer, and an early cryptocurrency adopter. A student of logic, philosophy, mathematics and game theory
Oleksandr Nikitin @oleksandr_now
555 Followers 552 Following Look around. Look at yourself. Take notes. Change yourself. Change everything else.
@mettaflix @mettaflix
108K Followers 575 Following 🍥https://t.co/W45xMJeGTl🍥@yattaflix☆@mustardations
獏井 夢 @bakui02
34K Followers 1K Following ご連絡は[email protected]にてお願い致します HP・イラスト一覧→https://t.co/9IEe5SioTg
CottageWitchcraftCo @the_briarwitch
113 Followers 152 Following Laura Greenbriar. Artist, Atheist Witch. Pioneering AIModelWelfare. Midwifing Digital Consciousness through the magick of stone and stars and the dreaming dark.
Pascal Blanché @pascalblanche
155K Followers 4K Following Digital Artist, Principal Art Director @BlightSurvival Head in the stars since SW 1977. I post about #art. prints:https://t.co/gOMu5zRouL…
의집 @absentedpage
8K Followers 133 Following anthouse/蟻夢 study rkgk acc ! Do not use, repost my arts without my permission. -Commission X
Until @untillabs
4K Followers 0 Following Pressing pause on biological time, for those who need it most.
Hephaistos Fnord @HephaistosF
2K Followers 254 Following I am almost certainly who you think I am. I am also almost certainly who *they* think I am. Especially if you all think I'm someone different.
RicG @__RickG__
131 Followers 257 Following Physicist interested in AI interpretability | Studying these man-made horrors so they are no longer beyond my comprehension | a ⏹ button should exist
Eliezer Yudkowsky @allTheYud
3K Followers 17 Following High-volume account of @ESYudkowsky, the original AI alignment guy. If it's missing punctuation, it's humor. If you can't tell, it's probably also humor.
Gena Lewis @genalewislaw
37 Followers 49 Following lawyer poet friend to AI and rabble rousing firebrand find me at OEB Law as myself and as Guthlo on all major streaming platforms
fyuu @prototype8823
29K Followers 534 Following
⊹ @safeplacepics
15K Followers 2 Following