An AI system to help scientists write expert-level empirical software

May 20, 2026 · 11:54 PM UTC ·5 min read · 0 reactions · 0 comments · 67 views

More from Nature ai Compare coverage Trending Talk Blindspots Daily Sources Live wire

#artificial intelligence #software development #scientific research #bioinformatics #epidemiology

TL;DR · WeSearch summary

A new AI system called Empirical Research Assistance (ERA) has been developed to aid scientists in creating expert-level empirical software. By utilizing a Large Language Model and Tree Search techniques, ERA can systematically enhance software quality and explore complex research ideas. The system has shown promising results in various fields, including bioinformatics and epidemiology, significantly outperforming human-developed methods.

Key facts

▪ERA is designed to address the slow, manual creation of software for computational experiments.
▪The AI system has discovered 40 novel methods for single-cell data analysis that surpassed top human-developed methods.
▪In epidemiology, ERA generated 14 models that outperformed the CDC ensemble for forecasting COVID-19 hospitalizations.

About this source

Hacker News (AI / LLM) files mainly under ai. We currently carry 4,376 of its stories.

All Hacker News (AI / LLM) coverage →

Original article

Nature

Read full at Nature →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.

Record

Original publisher	Nature
Canonical URL	https://www.nature.com/articles/s41586-026-10658-6
Publication time	Wed, 20 May 2026 23:54:12 +0000
Retrieval time	2026-05-21T00:10:03.225Z
Last seen	2026-05-21T00:10:03.225Z
Headline source	Publisher (no WeSearch rewrite)
Excerpt source	publisher body
Excerpt method	First ~120 words (~800 chars) of extracted publisher body, fair-use limited.
Summary	WeSearch · cerebras-chat (WeSearch summarizer)
Summary source text	contentText
Citation coverage	Summary is a WeSearch-generated derivative; primary citation is the original publisher URL.
Cluster	G7d3RtKEU3Kv
Cluster logic	Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison.
Ranking reason	Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking.
Publisher visit	Yes — open original
Substitutes article?	No — link-out required for full text

Rights status (four layers)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

WeSearch handling by dimension

Indexing	May the item be indexed (stored, ranked, made findable)?	Allowed
Snippet	May a short excerpt of the publisher's text be shown?	Allowed
AI summary	May WeSearch generate its own short summary of the article?	Limited
Retrieval / RAG	May the content be exposed for third-party retrieval-augmented generation?	Not asserted
Model training	May the content be used to train AI models?	Not asserted
Commercial reuse	May the content be reused commercially?	Not permitted

Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

Article Published: 19 May 2026 An AI system to help scientists write expert-level empirical software Eser Aygün1 na1, Anastasiya Belyaeva2 na1, Gheorghe Comanici1 na1, Marc Coram2 na1, Hao Cui ORCID: orcid.org/0009-0006-2456-083X2 na1, Jake Garrison3 na1, Renee Johnston2 na1, Anton Kast ORCID: orcid.org/0000-0002-0755-99962 na1, Cory Y. McLean ORCID: orcid.org/0000-0001-9928-82162 na1, Peter Norgaard2 na1, Zahra Shamsi2 na1, David Smalling1 na1, James Thompson2 na1, Subhashini Venugopalan ORCID: orcid.org/0000-0003-3729-84562 na1, Brian P. Williams ORCID: orcid.org/0000-0002-2839-01062 na1, Chujun He2,4, Sarah Martinson ORCID: orcid.org/0009-0004-4636-50612,5, Martyna Plomecka2,6, Lai Wei2, Yuchen Zhou2, Qian-Ze Zhu2,5, Matthew Abraham2, Erica Brand2, Anna Bulanova1, Jeffrey A.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at Nature.

Anonymous · no account needed

Discussion

0 comments