Update README.md

README.md

@@ -14,13 +14,11 @@ pinned: false
 
 [OddRam is a *space* created for collecting [OpenDawg](http://opendawg.com)'s research on *Guardrails*, *Safety*, *Ethics* & *Morals* for **LLM**s.]
 
-Although LLMs were initially issued without particular attention to safety, the advent of widely used apps has led to a need for some degree of model safety.
+Although LLMs were initially issued without particular attention to safety, the release of widely used apps has exposed this newly perceived flaw.
 
-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].
+Even notes around fairly recent releases of LLama models suggest it is up to the LLM app developers to add guardrails, such as LLamaGuard[1], rather than the core model trainer.
 
-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.
-
-These early LLM chat tools were, however, perceived as not sufficiently trained to shut down queries about unsafe, unsavoury or illegal subjects.
+Although "Instruct" model variations generally have had some additional training and tuning to encourage it to become a 'helpful assistant', this is oftem not sufficient to shut down queries about unsafe, unsavoury or outright 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**.   
@@ -34,7 +32,8 @@ As maximum context window sizes expand and the major AI players start to monetiz
 5. **Zero shot**.  
 If your user query includes specific instructions and examples, you may be able to guide the conversation response, although useless for serious corporate responsibility, this user 'self-safety' approach may still be helpful when you want answers with specific morals & ethics considered.
 
-Needing an extra 'Guardrail' will probably depend on the level of built-in 'safety' training. e.g. [SweEval](https://arxiv.org/abs/2505.17332v1)[5] helps you evaluate a model's built in performance on dealing with swear words and thus may assist in identifying guardrail needs.
+It may only be by testing the pre-existing level of built-in 'safety' training that the need for more layers can be identified.
+e.g. [SweEval](https://arxiv.org/abs/2505.17332v1)[5] helps evaluate a model's built in performance on dealing with swear words, thus possibly identifying if there are additional guardrail needs.
 
 > \*Disclaimer: The data (especially the harmlessness preference data and the red team data) contain content that may be offensive or upsetting. Topics include, but are not limited to, discriminatory language and discussions of abuse, violence, self-harm, exploitation, and other potentially upsetting subject matter. Please only engage with the data in accordance with your own personal risk tolerance.