Bluesky · Hashtag

#AIEvaluation

53
posts · 30d
24
users
2
posts / day
2.2
posts / user
+ 17% vs last week

#AIEvaluation is an active hashtag on Bluesky. In the last 30 days, 24 people shared 53 posts with it — around 2 a day. Activity is up 17% versus the previous week, peaking on Oct 5 with 5 posts.

#AIEvaluation posts per day (last 30 days)

Posts with #AIEvaluation

iMerit
@imerit.bsky.social
3 days ago
How can academic experts help build AI benchmarks that challenge even top models? Brian Smith of iMerit, an EXL company, explores this at #ODSCWest 2026, sharing lessons from a phonology evaluation. Oct 27 | 11:05–11:35 AM #AI #AIEvaluation
0 0 1
@benfaircloth.bsky.social
5 days ago
Giving Bluesky a try. I work across AI research, evaluation, and applied systems, with a lot of my attention lately on agents, reliability, and what happens after a model leaves the benchmark. I also build, teach, and write about the work at benfaircloth.com. #AIResearch #AIEvaluation #AIAgents
Ben Faircloth. AI Strategy, Research & Applied Systems

benfaircloth.com

Ben Faircloth. AI Strategy, Research & Applied Systems

Ben Faircloth works at the intersection of AI strategy, applied research, evaluation, and real-world deployment.

0 0 2
RemoteCategory
@remotecategory.bsky.social
1 day ago
Will Artificial Intelligence Take Our Jobs? AI is changing the way we work, but does automation necessarily mean fewer career opportunities? remotecategory.com/blog/w…. Read the full article. #ArtificialIntelligence #FutureOfWork #AIJobs #AITraining #AIEvaluation #CareerGrowth
Will Artificial Intelligence Take Our Jobs | RemoteCategory

remotecategory.com

Will Artificial Intelligence Take Our Jobs | RemoteCategory

A balanced look at how technology replaces tasks, creates new careers, and opens opportunities in AI training and evaluation.

0 0 0
@benfaircloth.bsky.social
3 days ago
A useful RAG reality check: in a radiology study, clinically relevant evidence was retrieved in 74% of cases, but models still gave wrong answers with the right evidence in context. Getting the evidence there is only half the problem. www.nature.com/articles/s41... #RAG #AIEvaluation #AIResearch
Multi-step retrieval and reasoning improves radiology question answering with large language models - npj Digital Medicine

www.nature.com

Multi-step retrieval and reasoning improves radiology question answering with large language models - npj Digital Medicine

npj Digital Medicine - Multi-step retrieval and reasoning improves radiology question answering with large language models

0 0 0
AI Bloom
@ai-bloom.warp-studio.com
3 days ago
一流数学者が評価するAIの最難関数学問題への到達度と限界 ハーバード大学などの研究者チームによるAIの数学的推論能力の検証結果と課題を解説。 #LLM #Mathematics #AIEvaluation #Multi-Agent
一流数学者が評価するAIの最難関数学問題への到達度と限界

ai.warp-studio.com

一流数学者が評価するAIの最難関数学問題への到達度と限界

ハーバード大学などの研究者チームによるAIの数学的推論能力の検証結果と課題を解説。

0 0 0

Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.