6 min read

Where AI drug discovery actually stands

Where AI drug discovery actually stands
Nº 01 · The Lede Hacker News Drug discovery · Computational

AI drug discovery, audited

AI drug discovery, audited
Fig. IHacker News · Filed 17 Aug 2026.

AI drug discovery gets audited in a Science.org blog post organized around three questions: what the term actually covers, where the field stands now, and what the path forward looks like. It drew 136 points and 71 comments on Hacker News over the weekend. Definitional discipline is the contribution here. Separating the steps where machine learning has moved real numbers from the steps where attrition looks unchanged since 2010 gives the field a shared vocabulary for its central argument, and it resets the reference point that every AI-discovery claim now gets measured against.

Read the source

Britain's AI scientist arrives
Fig. IIX · Filed 17 Aug 2026.
Nº 02 X Field report

Britain's AI scientist arrives

Inherent Labs released its first research: an AI scientist pairing model intuition with agents, aimed at climate science, structural biology, and materials science in one system. Cross-domain scope is the claim to watch. Most scientific agents so far have been narrow by construction, so a single stack that treats structural biology as one instance of a general research loop tests whether generality survives contact with biology's messiest data. Britain also gains a named entrant in a race so far dominated by US labs.

Read more
A foundation model for science
Fig. IIIarXiv · Filed 17 Aug 2026.
Nº 03 arXiv Field report

A foundation model for science

A science-specific foundation model landed on arXiv: Intern-S2-Preview, built for agentic research work rather than chat, with the pitch that tool use and multi-step research behavior are trained in rather than bolted on by prompting. Purpose-built science models are hardening into a category of their own, which reopens a question a recent benchmark tested head-on — whether general frontier models stay the default substrate for discovery agents, or whether domain-trained ones take over the parts of biology where literature, structures, and assay data all have to be read at once.

Read more
Also Filed · Four Briefs from the queue
Nº 04 bioRxiv Field report

Multi-omics by conversation

Conversational agents run multi-omics end to end in a new bioRxiv preprint, coordinating specialist agents across data types behind a single chat interface. Natural-language orchestration moves integrative multi-omics from a specialist craft toward something queryable.

Read
Nº 05 bioRxiv Field report

Self-checking image registration

ACCREDIT registers images at cell resolution across modalities, with an agent that grades its own output and re-tunes the alignment until quality clears a bar. Self-checking registration closes a step where cross-modal spatial work still leans on eyeballing overlays.

Read
Nº 06 arXiv Benchmarks · Evaluation

Benchmarking research ideas

LigBench scores research ideas against human judgment, folding scattered evaluations of LLM-generated hypotheses into one benchmark. Idea quality becomes measurable, which is the missing piece in every claim that an agent proposed a novel hypothesis.

Read
Nº 07 X Field report

Dog vaccine to YC

An AI-designed dog cancer vaccine became a Y Combinator startup, according to an X post over the weekend that offers little past the claim itself. Veterinary oncology keeps looking like the shortest route from a generated design to a treated patient.

Read

Reply with your discoveries. A human reads them. Forward freely.

Agentic Discovery  ·  Nº 78  ·  17 Aug 2026

Editor's Note

Monday: the field's honest scorecard outdrew every launch post this weekend, and a new AI scientist arrived from Britain.

 

Nº 01 · The Lede  —  Hacker News  —  Drug discovery · Computational

AI drug discovery, audited

AI drug discovery, audited

Fig. I  Hacker News · Filed 17 Aug 2026.

AI drug discovery gets audited in a Science.org blog post organized around three questions: what the term actually covers, where the field stands now, and what the path forward looks like. It drew 136 points and 71 comments on Hacker News over the weekend. Definitional discipline is the contribution here. Separating the steps where machine learning has moved real numbers from the steps where attrition looks unchanged since 2010 gives the field a shared vocabulary for its central argument, and it resets the reference point that every AI-discovery claim now gets measured against.

Read the source →

Why it matters

Field-level scorecards are becoming the thing AI-discovery claims get checked against, and the burden of proof is shifting from "our model predicts binding" to show me where in the pipeline that changed an outcome.

 

Nº 02  —  X  —  Field report

Britain's AI scientist arrives

Fig. II  X · Filed 17 Aug 2026.

Britain's AI scientist arrives

Inherent Labs released its first research: an AI scientist pairing model intuition with agents, aimed at climate science, structural biology, and materials science in one system. Cross-domain scope is the claim to watch. Most scientific agents so far have been narrow by construction, so a single stack that treats structural biology as one instance of a general research loop tests whether generality survives contact with biology's messiest data. Britain also gains a named entrant in a race so far dominated by US labs.

Read more →

 

Nº 03  —  arXiv  —  Field report

A foundation model for science

Fig. III  arXiv · Filed 17 Aug 2026.

A foundation model for science

A science-specific foundation model landed on arXiv: Intern-S2-Preview, built for agentic research work rather than chat, with the pitch that tool use and multi-step research behavior are trained in rather than bolted on by prompting. Purpose-built science models are hardening into a category of their own, which reopens a question a recent benchmark tested head-on — whether general frontier models stay the default substrate for discovery agents, or whether domain-trained ones take over the parts of biology where literature, structures, and assay data all have to be read at once.

Read more →

 

Also Filed  ·  Four Briefs from the queue

Nº 04  —  bioRxiv  —  Field report

Multi-omics by conversation

Conversational agents run multi-omics end to end in a new bioRxiv preprint, coordinating specialist agents across data types behind a single chat interface. Natural-language orchestration moves integrative multi-omics from a specialist craft toward something queryable.

Read →

Nº 05  —  bioRxiv  —  Field report

Self-checking image registration

ACCREDIT registers images at cell resolution across modalities, with an agent that grades its own output and re-tunes the alignment until quality clears a bar. Self-checking registration closes a step where cross-modal spatial work still leans on eyeballing overlays.

Read →

Nº 06  —  arXiv  —  Benchmarks · Evaluation

Benchmarking research ideas

LigBench scores research ideas against human judgment, folding scattered evaluations of LLM-generated hypotheses into one benchmark. Idea quality becomes measurable, which is the missing piece in every claim that an agent proposed a novel hypothesis.

Read →

Nº 07  —  X  —  Field report

Dog vaccine to YC

An AI-designed dog cancer vaccine became a Y Combinator startup, according to an X post over the weekend that offers little past the claim itself. Veterinary oncology keeps looking like the shortest route from a generated design to a treated patient.

Read →

 

· · ·

Reply with your discoveries. A human reads them. Forward freely.