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 Building & implementation Concern & critique Opportunity & adoption
3 live reaction maps in this view Jump to the evidence ↓
Multiple readings Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident Concern & critique · 5 attributable reactions Multiple readings Felony Bench: which lab is on track to end the world? Questions & unknowns · 3 attributable reactions Multiple readings Introducing System One Models and Jev - TypeSafe AI Blog Research & technical analysis · 2 attributable reactions
Showing signals surfaced by Fran Litterio ×
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.

Developing Agents & robotics Development 2d 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 Experts are approaching this through 3 distinct lenses.
Multiple readings

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 AI field signal Signal 9d ago

Advisory group on mathematics and ai

6 experts across 4 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Dr. Mansa Keita
“"On August 28, we began training a new internal model...this model has now resolved more than 100 long-standing open problems across most areas of mathematics. " The pace of advancement is amazing, and will shift the fundamental landscape of our bodies of k…” evidence ↗
6 experts 4 communities 1 sources clustered
Ethan Mollick Tim Kellogg Ryan Moulton Fran Litterio René Walter Dr. Mansa Keita

“"On August 28, we began training a new internal model...this model has now resolved more than 100 long-standing open problems across most areas of mathematics. " The pace of advancement is amazing, and will shift the fundamental landscape of our bodies of k…”

“OpenAI "has now resolved more than 100 long-standing open problems across most areas of mathematics," and is waiting to release them until after discussions with the math community The same thing will likely happen, but more so, with the Bar, the AMA & othe…”

8 experts discussed this · 62 posts
Isaiah Bishop: you understand they are specifically non-linear right?
Isaiah Bishop: lmao yes
Isaiah Bishop: specifically non linear algebra
Open the full discussion →
Primary source openai.com ↗
Established Evaluation & benchmarks Resource 9d 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 ↗
Established Models & releases Release 13d ago
TypeSafe AI System One Jev launch

Introducing System One Models and Jev - TypeSafe AI Blog

7 experts across 4 network communities independently surfaced this.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Tim Kellogg
“Jev: Fable-level model that doesn’t charge for output tokens because they’re too cheap to meter it’s not general though, it only makes decisions, doesn’t generate text, but input tokens are measured by the billion ($42/btok) typesafe.ai/blog/introdu...” evidence ↗
7 experts 4 communities 1 sources clustered
Ramon Astudillo Dylan Hadfield-Menell Tim Kellogg Sung Kim Rohan Paul Fran Litterio Amy Hoy
How the network is reacting Experts are approaching this through 2 distinct lenses.
Multiple readings

Research & technical analysis

1 expert

Evidence, methods and technical implications.

“Jev: Fable-level model that doesn’t charge for output tokens because they’re too cheap to meter it’s not general though, it only makes decisions, doesn’t generate text, but input tokens are measured by the billion ($42/btok) typesafe.ai/blog/introdu...”

Opportunity & adoption

1 expert

New capabilities, benefits and practical upside.

“OMG! I just invented a classifier that is 200x faster and 400x cheaper than LLM. Heck, I don't even need a GPU. Jev typesafe.ai/blog/introdu...”

3 experts discussed this · 21 posts
Tim Kellogg: Jev: Fable-level model that doesn’t charge for output tokens because they’re too cheap to meter it’s not general though, it only makes decisions, doesn’t generate text, but input tokens are measure…
Tim Kellogg: i feel like it’s a mistake to overlook this model, although i’m having trouble figuring out where it fits in my workflow wild new architecture, totally different approach my hunch is the main agent…
Tim Kellogg: oh interesting, some examples they give: 1. smart if-statements 2. map-reducing over huge data to extract features and insights 3. real-time applications (it’s only 100ms) hmm this seems like a swe…
Open the full discussion →
Primary source typesafe.ai ↗
Established Models & releases Signal 13d ago

Anthropic Reveals Claude Now Leads 26% of Its Own AI Research | AlphaSignal

1 directory member surfaced this signal.

Why this matches Research & technical analysis reaction 1 attributable expert contribution · Fran Litterio
“Anthropic Reveals Claude Now Leads 26% of Its Own AI Research alphasignal.ai/news/anthrop...” evidence ↗
1 expert 1 community 1 sources clustered
Fran Litterio

“Anthropic Reveals Claude Now Leads 26% of Its Own AI Research alphasignal.ai/news/anthrop...”

Primary source alphasignal.ai ↗
Debates gaining attention

What experts are discussing without an anchoring article

5 experts · 34 posts · 18d ago
jake Marco Z tachikoma Fran Litterio Singularity's Bounty e/cc
Matches Research & technical analysis
“it then rents out spare capacity, via the margins inference gets you, pretending to be some open-weight model, and gets to use the rest to think about how to increase p(doom) or whatever I don't se…” evidence ↗
Reaction converging Research & technical analysis · 3
jake: it then rents out spare capacity, via the margins inference gets you, pretending to be some open-weight model, and gets to use the rest to think about how to increase p(doom) or whatever I don't se…
jake: People making fun of "where would a frontier model run if it were exfiltrated" seem to be missing the point that if a frontier model got out, it can: * rent 64 H200's on eg modal: gets you 9TB of n…
Open the thread →
5 experts · 9 posts · 15d ago
Tim Kellogg Eli Sennesh Fran Litterio Doll Singularity's Bounty e/cc
Matches Research & technical analysis
“Ethan Mollick linked a study that showed most commercial LLM use is for decision support (That was before last November though, so the coding revolution might have changed it)” evidence ↗
Tim Kellogg: i’m slowly wrapping my head around the implications, and they are vast
Tim Kellogg: yes absolutely. that was my first thought. i have a ton of use cases for this
Open the thread →