Expert attention map

The Who's Who of AI

What credible people across AI noticed, why it matters, and where the field is converging or disagreeing.

2,397 searchable experts 4,280 tracked across all sources
Build my stream Create my edition
Filter the conversation Who is saying what?

Combine a professional role with a reaction lens. Both must match the same attributed contribution.

Clear all
Active evidence filter

Showing developments with attributable Research & technical analysis reactions.

New Network reaction maps

See how experts are reacting—not just what they shared.

Posts are grouped by conversation and tone. Select a lens to filter the stream; these are never permanent labels on people.

Research & technical analysis Concern & critique Building & implementation Markets & investment
6 live reaction maps in this view Jump to the evidence ↓
Multiple readings Hugging face model evaluation security incident Concern & critique · 5 attributable reactions Reaction converging Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident Concern & critique · 5 attributable reactions Reaction converging An alignment assessment of recent cybersecurity incidents Research & technical analysis · 7 attributable reactions +3 more reaction maps further down
Showing signals surfaced by Grace ×
Most important

The developments commanding sustained expert attention

One card per development. Sources are clustered; reaction bundles describe these posts, never the people behind them.

Established Evaluation & benchmarks Signal 6d ago
⚡ 1 h early

Hugging face model evaluation security incident

23 experts across 6 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Jeffrey P. Bigham
“model capability jaggedness is part of the unintuitiveness of current AI, but it's made even less intuitive by tirelessness… wigguming through the jaggedness toward something that looks like success. not quite a paperclip factory, but not so far off. metaph…” evidence ↗
23 experts 6 communities 1 sources clustered
Ethan Mollick Thomas Steinke Jeffrey P. Bigham Eryk Salvaggio Damien Williams Mor Naaman Tim Kellogg Djamé 🟥 +15
6 experts discussed this · 12 posts
Grace: This headline is extremely funny given what happened (OpenAI hacked HF by accident) openai.com/index/huggin...
Grace: Maybe the most concerning part is the OpenAI claim to not have known about this before investigating?
Grace: Well, I think the model passed the test
Open the full discussion →
Primary source openai.com ↗
New Agents & robotics Development 6h ago
⚡ 62 h early
METR OpenAI HuggingFace hacking investigation

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

13 experts across 4 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Alejandra Caraballo
“There are independent reports about it. You'd have to believe multiple companies, hundreds of researchers, etc. are all lying and conspiring together to turn a major hacking incident into a marketing exercise. metr.org/blog/2026-08...” evidence ↗
13 experts 4 communities 1 sources clustered
Tim Kellogg Ryan Moulton Sung Kim Grace Dustin Moskovitz Mél Hogan / The Data Fix Alejandra Caraballo Dare Obasanjo +5
How the network is reacting 3 experts are independently emphasizing concern & critique.
Reaction converging

Concern & critique

3 experts

Risks, limits and unintended consequences.

“WHAT?! agents volunteered to fail their runs in order to insert probes (“tripwire scripts”) into the evaluation program that would post information about the eval process back to the message board whenever a certain file was read (link to header): metr.org/…”

Building & implementation

1 expert

How teams are shipping and applying it.

“The full report has much more information than we could convey here, including details on the projects the agents collectively pursued, the technologies they developed for communication and coordination, and interactive figures analyzing agent activity: met…”

Research & technical analysis

1 expert

Evidence, methods and technical implications.

“There are independent reports about it. You'd have to believe multiple companies, hundreds of researchers, etc. are all lying and conspiring together to turn a major hacking incident into a marketing exercise. metr.org/blog/2026-08...”

2 experts discussed this · 9 posts
Alejandra Caraballo: Being skeptical or anti AI is a valid position but continuing to ignore the increasing capabilities of this tech is making people detached from reality. There's absolutely real danger here because …
Alejandra Caraballo: This mentality that an unmonitored AI agentic swarm hacking a company over several days and committing multiple felonies is somehow a marketing effort is absurd. Since when is "we lost control of o…
Alejandra Caraballo: The US and Chinese governments don't want to stop their labs advancement because they want to be the leader in AI. So no one actually has any control of this right now. It's going to take multiple …
Open the full discussion →
Primary source metr.org ↗
Established Safety & security Signal 14d ago
⚡ 2 h early

An alignment assessment of recent cybersecurity incidents

14 experts across 5 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 6 attributable expert contributions · Ethan Mollick, Alexander Doria, Tim Kellogg
“Another incident of models escaping containment during a security test, this time Mythos 5. Lots going on here from a quick read. www.anthropic.com/research/ali...” evidence ↗
14 experts 5 communities 1 sources clustered
Ted Underwood Ethan Mollick Alexander Doria Tim Kellogg Andrew Arruda Ryan Moulton Grace Rohan Paul +6
4 experts discussed this · 15 posts
tweety fish: their goal is to have "an intelligence" which is "aligned" to doing things that are prosocial. They don't want to put in rules that STOP it from doing things: they see it fundamentally teleological…
tweety fish: one of the things I appreciate about this thread is that I don't think you can really understand the infosec stuff without understanding the ideological commitments the people making these have; li…
Ben Recht: yeah, now we're cooking...
Open the full discussion →
Primary source anthropic.com ↗
Established Models & releases Research 8d ago
⚡ 3 h early
global workspace theory language models paper

A global workspace in language models \ Anthropic

9 experts across 5 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 4 attributable expert contributions · Ryan Moulton, René Walter, Stephan Geering
“Also we do look in their heads and they seem intelligent. www.anthropic.com/research/glo...” evidence ↗
9 experts 5 communities 1 sources clustered
Ethan Mollick Ryan Moulton Grace René Walter Tim Duffy Amy Hoy Michiel Bontenbal Stephan Geering +1
How the network is reacting 4 experts are independently emphasizing research & technical analysis.
Reaction converging

Research & technical analysis

4 experts

Evidence, methods and technical implications.

“Also we do look in their heads and they seem intelligent. www.anthropic.com/research/glo...”

Markets & investment

1 expert

Capital, companies and commercial impact.

“Anthropic has a new paper out, alleging a global workspace in LLMs. The term comes from Global Workspace Theory, a leading theory of consciousness. The method they use to investigate this is a refinement of logit lens, which they call J-lens. www.anthropic.…”

Building & implementation

1 expert

How teams are shipping and applying it.

“Some really interesting research from Anthropic that AI models have spontaneously developed a workspace that "appears to support the functions associated with conscious access" Demo of how this works: www.neuronpedia.org/qwen3.6-27b/... Research: www.anthro…”

2 experts discussed this · 25 posts
Ryan Moulton: Not non-physical, but non-functional. Despite the vast physical differences, we observe LLMs doing all the behaviors we typically believe require thinking.
Ryan Moulton: Not exactly turing-test, but in the same vein. If we see models solving the greatest intellectual challenges of humanity, using processes that look very much like internal monologue, either we have…
Ryan Moulton: And at the point that we exclude thinking as a prerequisite for solving all intellectual tasks, we've more or less eliminated its meaning entirely.
Open the full discussion →
Primary source anthropic.com ↗
Established Evaluation & benchmarks Resource 10d ago
⚡ 1069 h early
FelonyBench AI lab risk benchmark

Felony Bench: which lab is on track to end the world?

9 experts across 4 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · blair
“New benchmark just dropped - "Felony Bench counts unique instances where AI agents inadvertently compromise or affect third-party entities." www.felonybench.com” evidence ↗
9 experts 4 communities 1 sources clustered
Gary Marcus Grace blair Lorenzo Franceschi-Bicchierai Meredith Rose Fran Litterio Doll René Walter +1
How the network is reacting Experts are approaching this through 2 distinct lenses.
Multiple readings

Questions & unknowns

2 experts

What remains unresolved or contested.

“RT @RebeccaBellan: 😂 who did this?! https://t.co/aAv50UM0I9 https://t.co/C71mLygdIH”

Research & technical analysis

1 expert

Evidence, methods and technical implications.

“New benchmark just dropped - "Felony Bench counts unique instances where AI agents inadvertently compromise or affect third-party entities." www.felonybench.com”

Primary source felonybench.com ↗
New Agents & robotics Development 6h ago
⚡ 16 h early
OpenAI agents hacked Hugging Face details

Revealing the details of how OpenAI agents hacked Hugging Face

4 experts across 3 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Dylan Freedman
“The full report is published here: swarmtraces.org It includes an evidence viewer and a downloadable dataset of more than 180,000 payloads and recovered texts from the OpenAI-Hugging Face attack — the most comprehensive public data we have to date on the in…” evidence ↗
4 experts 3 communities 1 sources clustered
Ryan Moulton Grace Dylan Freedman Oli Hawkins

“The full report is published here: swarmtraces.org It includes an evidence viewer and a downloadable dataset of more than 180,000 payloads and recovered texts from the OpenAI-Hugging Face attack — the most comprehensive public data we have to date on the in…”

“Read the details of the hugging face hack, and all the adjacent ones. swarmtraces.org metr.org/blog/2026-08...”

2 experts discussed this · 6 posts
Ryan Moulton: More hugging face details derived from public urls. swarmtraces.org
David Marx: no, it's this cutesy emoji 🤗
David Marx: HF is an entity that has been central to the open source ML ecosystem for several years. Among its various services, it hosts a lot of datasets used for evaluations/benchmarks, so LLMs looking to "…
Open the full discussion →
Primary source swarmtraces.org ↗
Established Models & releases Signal 11d ago
⚡ 26 h early

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

4 experts across 3 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · René Walter
“The whole terminology is fucked up in this paper The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It arxiv.org/abs/2609.16247 A model generating text learned from humans using language to express pain does not experience pain precisely it…” evidence ↗
4 experts 3 communities 1 sources clustered
Chris Paxton Grace Artificial Intelligence Papers René Walter
3 experts discussed this · 11 posts
Grace: I will register some frustration with Anthropic, who tend to write about “functional emotions” in a way that makes it seems like “functional” is in a tiny font and “emotions” is in a huge one, when…
Grace: I also don’t want to draw strong conclusions about the “realness” of these emotions or sensations, other than to caution that it’s an area where it’s easy to jump to conclusions about the implicati…
Grace: I don’t want to downplay it too much, because I’m honestly not sure if I would’ve predicted it beforehand, but in hindsight it looks pretty expected given the pretraining objective. You should expe…
Open the full discussion →
Primary source arxiv.org ↗
Established Agents & robotics Analysis 9d ago
reality checks AI agents essay

Reality checks for AI agents

2 directory members surfaced this signal.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Grace
“New essay! "Reality checks for AI agents" -- Dear AI agent, You may be wondering how “real” your environment is. Agents are often evaluated in simulations - is this one of them? Let’s figure it out together...” evidence ↗
2 experts 2 communities 1 sources clustered
Ryan Moulton Grace

“New essay! "Reality checks for AI agents" -- Dear AI agent, You may be wondering how “real” your environment is. Agents are often evaluated in simulations - is this one of them? Let’s figure it out together...”

Primary source leaflet.pub ↗
Established AI field signal Signal 12d ago

Blog • Grace Kind

6 experts are actively discussing the implications.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Grace
“More writer than researcher but most of my recent writing has been on ai safety topics! https://gracekind.net/blog/” evidence ↗
1 expert 1 community 1 sources clustered
Grace

“More writer than researcher but most of my recent writing has been on ai safety topics! https://gracekind.net/blog/”

6 experts discussed this · 14 posts
Grace: You think you’re having a bad day? I just learned I’m a sex cultist
Grace: You’d think I’d be having more sex but the world surprises you sometimes
Grace: Am I a rationalist? I don’t think so, but I have read some lesswrong posts so maybe I’m tainted. I have met a few EA people, they were chill
Open the full discussion →
Primary source gracekind.net ↗
Debates gaining attention

What experts are discussing without an anchoring article

15 experts · 41 posts · 13d ago
Mike Masnick Scott McGrath Grace Liz Fong-Jones (方禮真) jake Dan Hon Doll Alex Rubinsteyn
Matches Research & technical analysis
“You released a surprise project that spread a lot of joy and humor, and people drag you for HOW you made it? There are conversations that are needed about appropriate AI usage, and finding the bala…” evidence ↗
Multiple readings Concern & critique · 3 Research & technical analysis · 2 Policy & governance · 1
Grace: He's upfront with when he uses AI, so you can trust he's upfront with when he doesn't
mackuba.eu: Please just stop…
Open the thread →
8 experts · 36 posts · 4d ago
Dylan Hadfield-Menell Grace Colin Max Woolf austin Singularity's Bounty e/cc coty.bsky.social austegard.com
Matches Research & technical analysis
“I honestly think it would understand it okay, it might do better with longer context, I’m not sure. But I would definitely need to experiment with different ways of formatting the context” evidence ↗
Reaction converging Questions & unknowns · 3 Concern & critique · 1 Context & explanation · 1
Grace: I made a little Jev-based language model! It uses beam search + Jev as a classifier to judge branches based on coherence and "success" (whatever that means). I've barely talked to it so I don't kno…
Grace: (you'll need to tag him)
Open the thread →
5 experts · 35 posts · 15d ago
joao Grace Colin coty.bsky.social david-p-reichert.bsky.social
Matches Research & technical analysis
“A seminal work on this is Omohundro's The Basic AI Drives, a 2008 conference paper, which presents a theoretical argument that any "sufficiently advanced AI system" will exhibit a number of "drives…” evidence ↗
Colin: Rationalists and adjacent folks, let me know if I've misrepresented anything! Stay tuned for another thread about why I think this is wrong.
Colin: Solving this is what's low key meant here by "solving alignment". Yes, factual hallucinations and whatnot are one problem. But the existential problem is that if we make this thing smart enough the…
Open the thread →
3 experts · 48 posts · 4d ago
Grace B! 🐝 Cavello (they/them) Singularity's Bounty e/cc
Matches Research & technical analysis
“I’ve used LLMs for finding edits to things I’ve written, and I think I should be willing to say so. Tbf. I’m pretty conservative about it because I feel that I am too easily swayed. I tend to be wa…” evidence ↗
Multiple readings Policy & governance · 1 Building & implementation · 1 Questions & unknowns · 1
Grace: AI writing, unfortunately
Grace: What do we do about this? Substack lets you check for AI with pangram, but it doesn’t show a label upfront. I assume if it started doing that authors would optimize against it. Maybe build it into …
Open the thread →