top | item 45719035 (no title) luke-stanley | 4 months ago Summarisation models that do not follow instructions already exist! Fixing exfiltration is good, low hanging fruit. But for a summarisation task, whole classes of typical instruction following behaviour are totally off target! discuss order hn newest simonw|4 months ago Which models do you recommend for that these days?Has the field moved on much since the pre-LLM-era models like T5?
simonw|4 months ago Which models do you recommend for that these days?Has the field moved on much since the pre-LLM-era models like T5?
simonw|4 months ago
Has the field moved on much since the pre-LLM-era models like T5?