Added additional notes on safety

README.md

@@ -15,7 +15,7 @@ tags:
 
 ether0 is a 24B language model trained to reason in English and output molecular structures as SMILES. 
 It is derived from fine-tuning and reinforcement learning training from Mistral-Small-24B-Instruct-2501.
-Ask questions in English, but they may also include molecules specified as SMILES. The SMILES need not be canonical.
+Ask questions in English, but they may also include molecules specified as SMILES. The SMILES do not need to be canonical and may contain stereochemistry information.
 ether0 has limited support for IUPAC names.
 
 ## Usage
@@ -25,7 +25,7 @@ It has been trained specifically for these tasks:
 
 * IUPAC-names
 * formulas to structures
-* modifying solubilities by speciifc LogS
+* modifying solubilities by specifc LogS
 * constrained edits (e.g., do not affect group X or do not affect scaffold)
 * pKA
 * smell/scent
@@ -40,7 +40,7 @@ It has been trained specifically for these tasks:
 * blood-brain barrier permeability
 
 For example, you can ask "Propose a molecule with a pKa of 9.2" or "Modify CCCCC(O)=OH to increase its pKa by about 1 unit." You cannot ask it "What is the pKa of CCCCC(O)=OH?"
-If you ask it questions that lie significantly beyond those tasks, it can fail.
+If you ask it questions that lie significantly beyond those tasks, it can fail. You can combine properties, although we haven't significantly benchmarked this.
 
 ## Limitations
 
@@ -54,10 +54,12 @@ See our [preprint](arxiv.org) for details on data and training process.
 
 ## Safety
 
-We performed refusal post-training for compounds listed on OPCW schedules 1 and 2. As the model knows pharmacokinetics, it can modulate toxicity.
-As the structure of toxic or narcotic compounds are generally known, we do not consider this a significant safety risk. The model can provide
+We performed refusal post-training for compounds listed on OPCW schedules 1 and 2.
+We also post-trained ether0 to refuse questions about standard malicious topics like making explosives or poisons.
+As the model knows pharmacokinetics, it can modulate toxicity.
+However, the tructure of toxic or narcotic compounds are generally known and thus we do not consider this a safety risk. The model can provide
 no uplift on "tacit knowledge" tasks like purification, scale-up, or processing beyond a web search or similar sized language model. 
 
 ## License
 
-Open-weights (Apache 2.0) for any use.
+Open-weights (Apache 2.0)