Update README.md

README.md

@@ -18,9 +18,11 @@ Although LLMs were initially issued without particular attention to safety, the
 
 e.g. Even notes around fairly recent releases of LLama models suggest it is up to the LLM app developer to add guardrails themselves, such as LLamaGuard[1].
 
-"Instruct" variations of LLMs generally have some additional training and tuning to encourage the model to act as a helpful assistant, rather than simply as an auto-complete bot or 'Raw' model but these LLMs were perceived as not sufficiently trained to shut down many queries about unsafe, unsavoury or illegal subjects.
+Initially "Instruct" variations of LLMs generally had some additional training and tuning to encourage the model to act as a 'helpful assistant', rather than simply as an auto-complete bot or 'Raw' model.
 
-Whilst researching we have different severasl approaches to addressing these issues from the model releasing community:
+These early LLM chat tools were, however, perceived as not sufficiently trained to shut down queries about unsafe, unsavoury or illegal subjects.
+
+Whilst researching; we have identified some of the possible approaches currently available to the model releasing/using community:
 1. **Fix The Training data**.   
 New models may have extensive "cleaning" of training data sets to remove unwanted inputs. This may be done manually or synthetically, probably mostly the latter. Essentially trying to mitigate the 'garbage in garbage out' syndrome.
 2. **Guards**.