"Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange" This paper shows how to turn AI from a single helpful assistant into a decentralized scientific lab. With many autonomous agents independently run tools, exchange traceable research
RESEARCH
-
Emerging AI Stack: Grok for Research, Claude for Building
By
–
There’s an emerging default stack: Grok for research, Claude for building.
-
MCP for arXiv: Research Agents Access Millions Papers
By
–
Introducing MCP for arXiv
— alphaXiv (@askalphaxiv) 17 mars 2026
Let your research agents stand on the shoulders of giants
Fast multi-turn retrieval, keyword search, and embedding search tools across millions of arXiv papers 🚀 pic.twitter.com/qFWwzWynGDIntroducing MCP for arXiv Let your research agents stand on the shoulders of giants Fast multi-turn retrieval, keyword search, and embedding search tools across millions of arXiv papers
-
3D Model Processing and Geometric Transformations in AI Pipelines
By
–
Hypothetically, if the full pipeline can be shown to do rotations/transformations, then by your explanation of geometric transformations above, then it *must* be processing 3D model data?
-
Mixed Results: Diffusion in Text, AR in Images, Hybrid Architectures
By
–
honestly its gotten more mixed. diffusion in text, AR in images. hybrid archs everywhere (altho most researchers tell me the differences between SSM vs transformers not that material). not clear.
-
Bullshit Benchmark: AI Evaluation Dataset and Viewer Tool
By
–
Github: https://
github.com/petergpt/bulls
hit-benchmark
… Data viewer: https://
petergpt.github.io/bullshit-bench
mark/viewer/index.v2.html
… -

GPT-5.4 Mini and Nano Score Low on BullshitBench
By
–
BullshitBench update: The new GPT-5.4 mini and nano models score quite low. This screenshot shows OpenAI models only, on the full list would put GPT-5.4-mini around 40th place and Nano is around 70th place. Again thinking didn't help much at all. https://t.co/EdwOBStKa4 pic.twitter.com/mxBGoFUzio
— Peter Gostev (@petergostev) 17 mars 2026BullshitBench update: The new GPT-5.4 mini and nano models score quite low. This screenshot shows OpenAI models only, on the full list would put GPT-5.4-mini around 40th place and Nano is around 70th place. Again thinking didn't help much at all.
-

Reasoning Approaches Show Limited Effectiveness in AI Systems
By
–
Another confirmation that reasoning doesn't seem to help
-
Robotics advances faster through pragmatism over dogmatism
By
–
Robotics is advancing rapidly: we can move even faster by being more pragmatic and less dogmatic. Excellent summary by @AnneliesGamble: Annelies Gamble (@AnneliesGamble) x.com/i/article/203395133152… — https://nitter.net/AnneliesGamble/status/2033954294614098160#m
→ View original post on X — @ken_goldberg, 2026-03-17 19:47 UTC
-
Hinton’s Views Not Representative of All AI Researchers
By
–
not everything Hinton says is representative of all or most AI researchers.
