/Tech10h ago

Bo Wang, University of Toronto professor, reports Claude Fable 5 successfully executed an autonomous drug design loop

The AI generated candidates for nine of 14 targets

512883511357.5K

Original post

Claude Fable 5 is also an amazing biology model! It just ran an autonomous drug design loop. 14 protein targets. No human. 9/14 (64%) yielded promising candidates.

This is quite remarkable that a model identifies binding sites, runs bioinformatics pipelines, and recovers from its own failures.

That's not a benchmark. That's a drug discovery engine. The 10x acceleration in AI-enabled drug discovery is well underway! 🔥🔥

Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

11:00 AM · Jun 9, 2026 · 57.5K Views

/Tech10h ago

Bo Wang, University of Toronto professor, reports Claude Fable 5 successfully executed an autonomous drug design loop

The AI generated candidates for nine of 14 targets

512883511357.5K

#925

Original post

Bo Wang@BoWang87

Claude Fable 5 is also an amazing biology model! It just ran an autonomous drug design loop. 14 protein targets. No human. 9/14 (64%) yielded promising candidates.

This is quite remarkable that a model identifies binding sites, runs bioinformatics pipelines, and recovers from its own failures.

That's not a benchmark. That's a drug discovery engine. The 10x acceleration in AI-enabled drug discovery is well underway! 🔥🔥

Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

11:00 AM · Jun 9, 2026 · 57.5K Views

Sentiment

Positive users praised Claude Fable 5 for autonomously designing drugs as an exciting agentic breakthrough, while negative users accused the claims of being lies or sales hype and complained about overly restrictive safety measures.

Pos

19.4%

Neg

80.6%

32 comments with sentiment.

Cluster Engagement

Posts from X

Most Activity

VIEWS2.7KBOOKMARKS2LIKES61REPLIES3

Derya Unutmaz, MD@DeryaTR_

@BoWang87 How?? I got flagged even for this!

10h2.7K612

RETWEETS1

Tristan Farmer@001TMF

@BoWang87 1. Not crazy really. Opus and even sonnet can run design loops. 2. Image showed mini binders and all in silico candidates no lab mention. 3. It’s unusable for bio/bio locked so can’t verify therefore not reliable.

Benchmarks look insane but it’s just not usable

6h5864

Anthony@anthonystaj

@BoWang87 can you post proof this happened? everyone else in the community is getting blocked for sayin hi to Fable but you were able to do novel drug discovery?

6h3608

Dr. Alex Tatem@DrAlexTatem

@BoWang87 TF are you talking about? It blocks any discussion of biology whatsoever 😂

3h33831

Dr. Datta M.D. (Radiology) M.B.B.S. 🇮🇳@DrDatta_AIIMS

@BoWang87 Crazy!

9h62831

Peter Ciaccia@PeterCiaccia

@BoWang87 how? I'm building biology software but am currently getting flagged for trying to implement multithreading and for basic webgl rendering...

9h4276

BioLLM@BioLLM_

@BoWang87 Look but don’t touch right? Censorship.

10h20121

anabology@anabology

@BoWang87 If only we could use it

8h5488

Ash Jogalekar@curiouswavefn

Are you in a special access program? It seems to be rejecting basically every biology and drug discovery prompt I am throwing at it. Also, the capabilities you are describing are present in Codex as well. Last week I ran a 47-hour-long pipeline doing a full structure and ligand-based pipeline for six drug discovery targets; full tooling, error-handling and reasoning. What do you think is distinctive about Fable, specifically?

4h5064

Rogu@RomanGuy20

@DeryaTR_ @BoWang87 Every time I give a try to Anthropic, I remember why I love OpenAI the most out of frontier labs.

9h1438

Melinda B. Chu@MelindaBChu1

@BoWang87 Did you synthesize them or just computational benchmarks?

I guess you’re one of the lucky elites. Everyone else is poor plebeians.

5h2827

Connor@riegalski

@PeterCiaccia @BoWang87 I was able to get it to work on an LNP pipeline without issue. I turned off memory to prevent any old project threads from flagging

9h571

Jack Hansen@hansen_jack_

@BoWang87 Too bad it’s not smart enough to tell the difference between basic biology questions and engineering a bioweapon

7h1642

Aditya Lalchandani@Adityalch

@BoWang87 No one in bio or health can use it. Every single health related question is flagged as a security risk

7h2184

Srijit Iyer@srijitiyer

@BoWang87 how are you bypassing the restrictions?

9h1914

xxl@edinuhegale

@DeryaTR_ @BoWang87 That tweet was written by Claude. The drug design experiment it talks about is from Anthropic's introduction article to the new model. Guy isn't even writing his own posts, let alone doing research with Fable 5

7h1353

Mosses@MossesPKD

@BoWang87 The "Amazing" in question:

6h1183

Hongjian Zhou@itsEmZee_

@BoWang87 Is there anyway to try the pipeline? Or share how to bypass the Fable flagging issue?

10h5441

DLM@DLM93987699

@BoWang87 What the hell are you mumbling about? Like this model will discover new medicines for diseases? What are you? A sales person for Anthropic? You should be ashamed for even mentioning such complete nonsense.

8h1382

Phil Murray@43981li

@BoWang87 I’d call it a hypothesis discovery engine rather than a drug discovery engine at this point.

But it’s equally exciting 😉

7h3301