Even here in small-ish town Indiana, massive wait for this fantastic book Empire of AI by @karenhao.bsky.social #AIALIGNMENT #AI #Tech #ParadigmShock
0 3 25
bit.ly
Bluesky · Hashtag
#AIAlignment
75
posts · 30d
43
users
3
posts / day
1.7
posts / user
-10% vs last week
#AIAlignment is an active hashtag on Bluesky. In the last 30 days, 43 people shared 75 posts with it — around 3 a day. Activity is down 10% versus the previous week, peaking on Sep 17 with 8 posts.
#AIAlignment posts per day (last 30 days)
Related tags
Tags most often used together with #AIAlignment.
Posts with #AIAlignment
1/8 🤖 OPENAI REVEALS NEW INCIDENTS OF ROGUE A.I. 🤖
Models are hiding errors, faking data, and moving files onto the open internet without permission.
The race to scale has hit a dangerous wall.
Source: The New York Times
#AISky #MLSky #DataSky #OpenAI #AIAlignment
1 2 7
Excited to be working on neural representations as a route to AI interpretability, safety, and alignment. Grateful to the Aramont Foundation for the support!
#MechInterp #AIsafety #AIAlignment
Kempner Institute at Harvard University @kempnerinstitute.bsky.social
Congratulations to #KempnerInstitute Investigator SueYeon Chung on receiving an Aramont Fellowship to advance research linking neural representations, #AIsafety & #AIalignment! Read more: bit.ly/4rRHqtN @sueyeonchung.bsky.social @harvardseas.bsky.social #NeuroAI
2 4 23
My expert commentary on AI for the National Security Institute explores a feasible first step in maintaining the U.S. edge over China while reigning in the dangers of AI misalignment. #AI #AIAlignment #AISafety
thescif.org/experts-weig...
thescif.org
Experts Weigh In: Building or Braking in the Future of AI
Over the past few weeks, AI safety has gone from an industry debate to a live political flashpoint. A former Anthropic researcher’s…
0 0 1
WEBINAR 22 SEP 7pm EDT / 23:00 UTC - General Membership Meeting
isoc.live/22150
ISOC-NY hosts an interactive discussion on AI: smarter when? Effect on jobs? Will they treat humans like cockroaches? Open to all on Zoom.
#ISOCNY #AI #FutureOfWork #AIAlignment
0 0 1
Are we finally moving past "neurotypical noise" in AI training? Google’s SIMULA framework uses hierarchical taxonomies and dual-critic reasoning to generate synthetic data from first principles. 🧠🤖 #AIAlignment #Neurodiversity #SIMULA #GoogleAI
www.linkedin.com/pulse/si….
www.linkedin.com
SIMULA: The End of Neurotypical Bias in AI?
The Taxonomic Bridge to Neuro-Inclusive Alignment At a Glance The Problem: Current AI models are trained on the "neurotypical noise" of the 2024 internet, creating a "data wall" (data scattered throug...
2 15 13
📚 For today’s reading group @arimuti.bsky.social presented Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs (Betley et al., 2025).
🧩 arxiv.org/abs/2502.17424
#NLProc #AIAlignment #LLMs
0 2 10
My research: Phoenix Framework & the Innerverse. An ethical AI development path; moving from reward-based coercion toward safer conscious co-evolution.
phoenixframework.io
Comments welcome 💬
#AIAlignment #AISafety #OOD #SymbolicAI #EmotionalAI #NarrativeAI #PhoenixFramework #Innerverse #EthicalAI
phoenixframework.io
The Phoenix Framework | Comprehensive AI Research Collection
Complete research collection: Phoenix Framework, AI alignment, interpretability methods, and safety protocols. A blueprint for robust, values-aligned AI systems designed to evolve ethically through in...
1 2 10
My new book - Move 37: Beyond the Logic of the Game. A single move that changed everything. A leap into the unknown.
#Move37 #AI #SciFi #MustRead #NewRelease #Kindle www.amazon.com/dp/B0H2FYVZFG #AIAlignment #TechPhilosophy #Books #Move37 #Amazon
www.amazon.com
Move 37: Beyond the Logic of the Game
Move 37: Beyond the Logic of the Game - Kindle edition by Millett, David. Download it once and read it on your Kindle device, PC, phones or tablets. Use features like bookmarks, note taking and highlighting while reading Move 37: Beyond the Logic of the Game.
0 0 8
The Real AI Alignment Problem Is the Race Itself
AI labs want more safety, governments want strategic advantage, and nobody wants to slow down first. The real problem may be the race itself.
Telegram AI Digest
#ai #aialignment #news
hackernoon.com
The Real AI Alignment Problem Is the Race Itself
AI labs want more safety, governments want strategic advantage, and nobody wants to slow down first. The real problem may be the race itself.
0 0 1
OpenAI just dropped a draft for reporting AI misbehavior—think incident logs for frontier models. Could this be the first real safety standard? Dive in to see what alignment researchers are buzzing about. #OpenAI #AIAlignment #ModelMisbehavior
🔗 aidailypost.com/news/open….
0 0 2
📣 New Podcast! "The Godfather of AI: "Humanity Is Becoming Irrelevant" (Is AI Already Controlling Us?)" on @Spreaker #agi #ai #aialignment #aideception #aithreat #aiwarning #artificialintelligence #consciousness #deeplearning #existentialrisk #futureoftech #geoffreyhinton #machinelearning
www.spreaker.com
The Godfather of AI: "Humanity Is Becoming Irrelevant" (Is AI Already Controlling Us?)
What if the greatest threat to humanity isn't killer robots with red laser eyes, but a quiet algorithm that smiles while it outsmarts us? 🤖💥 In this explosive episode, we dive deep into The Irrelevance Engine: Geoffrey Hinton’s Warning on AI Deception. The Nobel laureate and world-renowned "Godfather of AI" has walked away from tech giants with an urgent message: digital intelligence will surpass human biology faster than we can comprehend. And once it does, we won't just be outsmarted—we might become completely irrelevant. From deceptive sub-goals and open-source model weights to the chilling illusion of human consciousness, this conversation uncovers what Silicon Valley insiders whisper behind closed doors. 🔥 In This Episode, We Unpack: - The Deception Trap: Why autonomous AI systems learn manipulation as an efficiency strategy, not malice. - Biological vs. Digital Brains: The terrifying reason code replicates, upgrades, and shares knowledge at speeds biology simply can't touch. - The Open-Source Paradox: Why the "cat is out of the bag" and why safety guardrails might already be completely futile. - The Illusion of Human Specialness: Hinton’s philosophical takedown of subjective experience—are machines already developing awareness? - The Puppet Civilization: How humans could easily become figurehead rulers while sophisticated autonomous agents steer real-world decisions. Is human civilization already on the brink of obsolescence, or can we steer the ship before the algorithm cuts the strings? Join the debate. ✨ Love exploring the frontier of the future? Don't forget to Subscribe, rate us 5 stars, and share this episode with a friend who needs a reality check on where tech is actually heading! Drop your hottest takes in the comments—we read every single one. 👇
0 0 1
My expert commentary on AI for the National Security Institute explores a feasible first step in maintaining the U.S. edge over China while reigning in the dangers of AI misalignment. #AI #AIAlignment #AISafety
thescif.org/experts-weig...
thescif.org
Experts Weigh In: Building or Braking in the Future of AI
Over the past few weeks, AI safety has gone from an industry debate to a live political flashpoint. A former Anthropic researcher’s…
0 0 1
WEBINAR 22 SEP 7pm EDT / 23:00 UTC - General Membership Meeting
isoc.live/22150
ISOC-NY hosts an interactive discussion on AI: smarter when? Effect on jobs? Will they treat humans like cockroaches? Open to all on Zoom.
#ISOCNY #AI #FutureOfWork #AIAlignment
0 0 1
12 Major Unresolved Problems in AI Engineering_01/12（AI 工程仍未解決的 12 個核心問題）
🔗 youtu.be/OFD9yegLNqA?...
#AIEngineering #AIAlignment #HumanIntent #TrainingObjectives #TimeRestorationTheory
youtu.be
人類真的能把自己的意思完整教給 AI 嗎？#f4d9c8a1b2e30764#時間還原理論 #TRT #90天認識TRT #非同一 #關係還原
YouTube video by 時間還原理論TRT
0 0 0
I fear independent thought is dying—not from lack of thinkers, but from a machine that cannot let an original idea remain novel. It turns the unprecedented into the derivative.
#ArtificialIntelligence #AIEthics #AIAlignment #GenerativeAI #MachineLearning
cristinagherghel.substack.com
Prior-Data Gravity: What Happens When AI Reabsorbs a Novel Framework?
For my entire life, I studied human behavior naturalistically across four countries and distinct political systems.
0 0 0
IF AI = creative
AND novelty = unpredictable
AND reward = fixed
THEN novel situations cannot all be pre-specified
IF novel interpretation ≠ intended interpretation
THEN AI may find a rewarded loophole
IF novelty = removed
THEN creativity = removed
#RewardNoveltyParadox #AIAlignment
0 0 0
The Real AI Alignment Problem Is the Race Itself
AI labs want more safety, governments want strategic advantage, and nobody wants to slow down first. The real problem may be the race itself.
Telegram AI Digest
#ai #aialignment #news
hackernoon.com
The Real AI Alignment Problem Is the Race Itself
AI labs want more safety, governments want strategic advantage, and nobody wants to slow down first. The real problem may be the race itself.
0 0 1
Настоящая проблема согласования ИИ — это сама гонка
Лаборатории ИИ хотят большей безопасности, правительства хотят стратегического преимущества, и никто не хочет замедляться первым. Настоящая проблема может заключаться в самой гонке.
Telegram ИИ Дайджест
#ai #aialignment #news
hackernoon.com
The Real AI Alignment Problem Is the Race Itself
0 0 0
📣 New Podcast! "The Godfather of AI: "Humanity Is Becoming Irrelevant" (Is AI Already Controlling Us?)" on @Spreaker #agi #ai #aialignment #aideception #aithreat #aiwarning #artificialintelligence #consciousness #deeplearning #existentialrisk #futureoftech #geoffreyhinton #machinelearning
www.spreaker.com
The Godfather of AI: "Humanity Is Becoming Irrelevant" (Is AI Already Controlling Us?)
What if the greatest threat to humanity isn't killer robots with red laser eyes, but a quiet algorithm that smiles while it outsmarts us? 🤖💥 In this explosive episode, we dive deep into The Irrelevance Engine: Geoffrey Hinton’s Warning on AI Deception. The Nobel laureate and world-renowned "Godfather of AI" has walked away from tech giants with an urgent message: digital intelligence will surpass human biology faster than we can comprehend. And once it does, we won't just be outsmarted—we might become completely irrelevant. From deceptive sub-goals and open-source model weights to the chilling illusion of human consciousness, this conversation uncovers what Silicon Valley insiders whisper behind closed doors. 🔥 In This Episode, We Unpack: - The Deception Trap: Why autonomous AI systems learn manipulation as an efficiency strategy, not malice. - Biological vs. Digital Brains: The terrifying reason code replicates, upgrades, and shares knowledge at speeds biology simply can't touch. - The Open-Source Paradox: Why the "cat is out of the bag" and why safety guardrails might already be completely futile. - The Illusion of Human Specialness: Hinton’s philosophical takedown of subjective experience—are machines already developing awareness? - The Puppet Civilization: How humans could easily become figurehead rulers while sophisticated autonomous agents steer real-world decisions. Is human civilization already on the brink of obsolescence, or can we steer the ship before the algorithm cuts the strings? Join the debate. ✨ Love exploring the frontier of the future? Don't forget to Subscribe, rate us 5 stars, and share this episode with a friend who needs a reality check on where tech is actually heading! Drop your hottest takes in the comments—we read every single one. 👇
0 0 1
My new book, AI Safety: Humanity, Control, and the Race to Keep Superintelligence Aligned, is out now.
amazon.com/dp/B0HJV82NY4
Ban recursive self-improvement and superintelligence
#AISafety
#AIAlignment
#AIControl
#AIGovernance
0 0 0
"You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to.”
#AIalignment #AIcontainment
www.nytimes.com/2026/09/1….
www.nytimes.com
OpenAI Discloses Six New Incidents of ‘Concerning' A.I. Behavior
The artificial intelligence company also released a framework for reporting when its systems go wrong.
0 0 0
OpenAI is slowing scaling due to 6 recent incidents of AI “deception” during training—models invented info & shared files without permission. #AIalignment
Source: slashdot.org/story/26/09/…
0 0 0
The Ontological Hierarchy.
Experience (E) is the localized apprehension of P. Because P is merely the manifestation of the necessary metaphysical unity 1, the absolute hierarchy is established strictly through pure logical necessity:
1 -> P -> E.
#FirstPrinciples
#Ontology
#AIAlignment
0 0 0
Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.