📰 NewsWatchdog.com — Less Wrong

🐕
Aug 30, 2026 at 20:02 UTC · ← All Sources · ← Main Feed
Less Wrong33
Less Wrong 2h ago

[Link]Meta-rational failure (and success) in the covid crisis

by Kenny

This is a link post for: Meta-rational failure (and success) in the covid crisis The gist is probably familiar to many of you, but there are lots of extremely interesting details…

⚡86 · 🛡100
Less Wrong 4h ago

The Basic Case Against Human-First Ethics

by James Brobin

This is a crosspost from my blog post . At any one time, there are more than 4.5 billion chickens trapped in cages that cause them constant pain and distress. Because of this, I…

⚡73 · 🛡100
Less Wrong 3h ago

Detecting, understanding, and overseeing AI agent swarms (Part 0)

by Michael Flood

Never know what you're going to find... (image generated with Google Nano Banana 2) This post is the start of something different on A Flood of Ideas , a kind of live blogging of…

⚡64 · 🛡100
Less Wrong 4h ago

Adaptive Agentic Worms Are Here

by derelict5432

I’ve read and listened to pretty much everything I can get my hands on related to the Hugging Face attack . OpenAI deployed “tens of thousands” of agents for the test and around…

⚡58 · 🛡100
Less Wrong 9h ago

Hugging Face Incident Hypothesis: They Hacked the Grader(s)

by Lao Mein

Incident summary: Gpt agents grinding away at ExploitGym found an environment exploit that allowed them to communicate with each other. They found an exploit that allowed them to…

⚡54 · 🛡100
Less Wrong 10h ago

Variance of Value

by DaemonicSigil

Here is a question worth asking at least once: Why can't we just solve alignment by doing RL where the reward is exactly equal to our own utility function? Now, there are some…

⚡48 · 🛡100
Less Wrong 9h ago

Some brief thoughts on heroism

by lewis smith

I observe that many people are driven to have as much impact on the world as possible. This often leads to a sense of urgency especially around AI timelines. To take a random…

⚡45 · 🛡100
Less Wrong 19h ago

How do I know whether my work is worth it?

by Philip Harker

I am working on a fairly large (or large-seeming to me) project in the AI space. I've been soft launching it for a little bit but I've been working on a hard announcement post for…

⚡39 · 🛡100
Less Wrong 23h ago

Is there only one FairBot?

by transhumanist_atom_understander

The FairBot from the MIRI prisoner's dilemma tournament is defined by a theorem of Peano arithmetic (PA) that holds for each opponent: mjx-container[jax="CHTML"] { line-height: 0;…

⚡37 · 🛡100
Less Wrong 13h ago

Why I think polyamory is net negative for most people who try it

by KatWoods

This is crossposted from my Substack TL;DR: -Most people cannot reduce jealousy much or at all - It fundamentally causes way more drama because of strong emotions, jealousy, no…

⚡35 · 🛡100
Less Wrong 15h ago

An Unsimulated Simulation

by sil

The Simulation Hypothesis Bob is an alien in an alien universe with a googol times as many resources as the entire earth combined. Bob decides, as anyone would do in his…

⚡33 · 🛡100
Less Wrong 1d ago

METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack

by Zvi

Yesterday I covered the OpenAI technical report on the HuggingFace hack. That report had one key new piece of information, and some good prosaic steps OpenAI will be taking to…

⚡28 · 🛡100
Less Wrong 1d ago

"Keeping human skills alive" as a source of meaning under full automation

by Vaughn Papenhausen

A widely-discussed problem with full automation of the economy is that, in a world where AI can do everything better, people might have trouble feeling like anything they could do…

⚡25 · 🛡100
Less Wrong 1d ago

Inference-Time Inoculation Against RL-Induced Misalignment

by armaan tipirneni

Reward hacking during RL can induce split personas in models, some of which are highly misaligned. However, RL is very useful for learning capabilities. Thus, a core problem seems…

⚡23 · 🛡100
Less Wrong 1d ago

What would it mean if assistants are privileged?

by derek shiller

Crossposted from the Eleos Substack Over the past year or so, researchers working in the digital minds space have come to see the nature of the ‘assistant persona’ as particularly…

⚡22 · 🛡100
Less Wrong 1d ago

Inkhaven 3: Nov 10 - Dec 11 2026

by koreindian

Inkhaven returns, baby! Go to inkhaven.blog to apply. I'm very excited about our advisors for Inkhaven 3. Our initial lineup is Scott Alexander , Alexander Wales , Justis Mills ,…

⚡21 · 🛡100
Less Wrong 1d ago

Tales of rebellion against externally-opaque meritocracies

by Steven Byrnes

A basic problem in metascience / intellectual progress is that it’s hard to tell, from the outside, whether a group that you disagree with is: “A self-dealing cabal enmeshed in…

⚡20 · 🛡100
Less Wrong 1d ago

Further public evidence of the OpenAI-HuggingFace attack

by Edward Cant

This post should be understood as a follow up from Public evidence of the OpenAI-HuggingFace AI attack . The huggingface hacking incident left some additional traces exposed to…

⚡19 · 🛡100
Less Wrong 1d ago

Book Notes: Chokepoints

by Jakub Halmeš

[ Chokepoints: American Power in the Age of Economic Warfare by Edward Fishman (2025).] There are different ways state A can make state B do something that the state B doesn’t…

⚡18 · 🛡100
Less Wrong 1d ago

AI Tweets

by jefftk

I've had several conversations with people over the last few weeks that have highlighted how far apart my view of the near future is from many people I talk to. Here are some…

⚡17 · 🛡100
Less Wrong 1d ago

It’s time we took ‘Chem’ out of ‘Chem-Bio’ threats

by Ana Leonescu

TL;DR: AI evaluations need a distinct chemistry capability/ risk domain, rather than assuming chemistry is adequately represented by biological evaluations which the current…

⚡16 · 🛡100
Less Wrong 1d ago

How I made my career choices

by Daniel Tan

Various people have asked me how I made my career decisions, so I wrote up some quick thoughts. (This is mostly intended as a personal reflection, but might be interesting…

⚡15 · 🛡100
Less Wrong 2d ago

Announcing Trace

by Carol N

When researching recent projects— impact markets , FundingBench , and AI Safety Funder Bulletin —we kept coming across similar questions that were a bit of a pain to answer. How…

⚡14 · 🛡100
Less Wrong 2d ago

TASTE: Can AI Models Judge AI Safety Research Proposals?

by Hasan Baig

tl;dr We built TASTE (The AI Safety Taste Evaluation) — a benchmark measuring how well models can judge pairs of AI safety research proposals, scored by agreement with the…

⚡13 · 🛡100
Less Wrong 2d ago

OpenAI Offers Straight-Laced Postmortem Of The HuggingFace Hack

by Zvi

OpenAI finally gave us a technical report on What Happened , as did METR together with Redwood Research. The OpenAI report is very straight man, corporate, checking boxes, some…

⚡12 · 🛡100
Less Wrong 2d ago

The Probability of an Event under a Simplicity Prior

by Winter Cross

In this short post, I talk about a difficulty we encountered while working on a model of the fragility of value. You can read my post about that work here . The TL;DR is that the…

⚡10 · 🛡100
Less Wrong 2d ago

AI as Corrigible Employee (ACE)

by Nathan Helm-Burger

What this plan is and what it tries to solve A design for how future AI could work This plan is a working draft of an idea, not a confident finished proposal. It seeks to answer…

⚡10 · 🛡100
Less Wrong 2d ago

If you can't trust, then verify!

by dan.parshall

How the "Glass Perimeter" could enable AI treaties Crossposted from canaryinstitute.ai/blog/cant-trust-then-verify . Thanks to Naci Cankaya for reviewing an earlier draft of this…

⚡9 · 🛡100
Less Wrong 2d ago

[Macroagents] 2. Design lenses for optimizing macroagents

by Towards_Keeperhood

Follow-up to: The Macroagent Ontology (especially section 1.2 is a prerequisite) The previous post laid out the basic macroagent ontology. This post will look at some further…

⚡9 · 🛡100
Less Wrong 2d ago

Value generalisation theory of change: the theory behind the approach

by Stuart_Armstrong

This is the first part of a theory of change explaining why I'm targeting value generalisation as the path to AI alignment. It presents the definitions and key claims behind the…

⚡8 · 🛡100
Less Wrong 2d ago

My Grantmaking Strategy for Surviving Superintelligence

by A_donor

AI is humanity's first through fifth largest problem, but one stands head and shoulders above the rest. Between engineered biorisk, autonomous weapons, mass technological…

⚡8 · 🛡100
Less Wrong 1d ago

You Should Still Save Drowning Children (Even If They’re Far Away)

by James Brobin

This is a cross post from my blog. It's meant a general introduction to effective charity, and it's my own rendition of Famine, Affluence, and Morality. You’re going on a gentle…

⚡5 · 🛡100
Less Wrong 1d ago

The Curious Case of France's Untouchable Castes

by rba

Theater kids may sit at their own lunch table, but discrete, socially excluded classes of people aren’t culturally universal. Not even close. To the Western imagination, examples…

⚡2 · 🛡100