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
Filter the conversation Who is saying what?

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

Clear all
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.

0 live reaction maps in this view

No development in this filter has enough independent reactions yet. The maps appear as soon as the evidence supports them.

Showing signals surfaced by Ai2 ×

The developments commanding sustained expert attention

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

Established Culture, work & education Development 4d ago
⚡ 6 h early
Ai2 Taylor Geospatial AI partnership

Ai2 and Taylor Geospatial partner to make geospatial AI easier to compare, run, and build on | Ai2

2 directory members surfaced this signal.

2 experts 2 communities 2 sources clustered

“We want input from the people who use these benchmarks. If you build, evaluate, or depend on geospatial foundation models, tell us which ones every model should be tested against. Read the announcement and share your input → buff.ly/pO8pNA0”

Established Evaluation & benchmarks Resource 8d ago
⚡ 4 h early
XYBench visual benchmark release

GitHub - allenai/XYBench

2 directory members surfaced this signal.

2 experts 2 communities 2 sources clustered

“Asking how to thicken frosting sliding off warm cupcakes? 🧁 Let them cool first! That’s the XY problem: seeking a fix that misses the real issue. XYBench tests whether LLMs spot & address it. 🏆 It won the Best Resource Award at EMNLP 2026! 🧵 buff.ly/cu7Bgwm”

Established Evaluation & benchmarks Resource 18d ago
AllenAI state-bench benchmark release

GitHub - allenai/state-bench

2 directory members surfaced this signal.

2 experts 2 communities 1 sources clustered

“Can LLMs track state changes over long texts—like an object changing hands or a variable reassignment? On our new StateBench eval, frontier models including GPT-6 Sol & Claude Opus 5.5 fell to 13% accuracy or lower on the hardest, longest problems. 🧵 buff.l…”

Established AI field signal Resource 15d ago
AllenAI ToyBlocks GitHub resource

GitHub - allenai/ToyBlocks

2 directory members surfaced this signal.

2 experts 2 communities 1 sources clustered

“We’re introducing ToyBlocks, an open simulated tabletop for controlled experiments in robot learning. It enables robotics researchers to experimentally control training data & models, run targeted evals, & trace failures to their causes. 🧵 buff.ly/0klTHYF”

Established Compute & infrastructure Development 10d ago
OLMo 3 earns Nextcloud ethical rating

How Olmo 3 earned the highest ethical rating from Nextcloud | Ai2

1 directory member surfaced this signal.

1 expert 1 community 1 sources clustered

“For open-source collaboration platform @nextcloud.bsky.social, local AI is only part of digital sovereignty. Users also need to inspect how a model was built. That’s why Nextcloud chose Olmo 3 to power AI in Nextcloud Assistant & its other apps. 🧵 buff.ly/B…”

Established Culture, work & education Development 17d ago
Ai2 Google climate model collaboration

Ai2 and Google collaborate on a new generation of climate models | Ai2

1 directory member surfaced this signal.

1 expert 1 community 2 sources clustered

“We’re teaming up with Google on NeuralGCM+ for faster, more reliable climate projections. Multimillion-dollar, 3-year funding from google.org & support from Google Research will expand our team—& we’ll open-source models & workflows. 🧵 buff.ly/ZIHkVju”

Established AI field signal Signal 18d ago

GitHub - allenai/state-bench

1 directory member surfaced this signal.

1 expert 1 community 1 sources clustered

“Can LLMs track state changes over long texts—like an object changing hands or a variable reassignment? On our new StateBench eval, frontier models including GPT-6 Sol & Claude Opus 5.5 fell to 13% accuracy or lower on the hardest, longest problems. 🧵 buff.l…”