Or just any other LLM even a smol one does a great job at it – cascading to two calls helps quite a bit!
PROMPT ENGINEERING
-
DRT-o1: Deep Reasoning Translation Optimizes Neural Machine Translation
By
–
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought Problem: Neural machine translation struggles with translating texts containing similes or metaphors, often failing to convey the intended meaning due to cultural differences and the limitations of literal
-
Align-Anything: Training Multimodal Models with Language Feedback
By
–
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback The paper introduces the Align-Anything framework to enhance all-modality models' alignment with human preferences using language feedback, improving instruction-following across text,
-
System prompts influence model responses
By
–
It’s evidence of that to the extent they’re wrong, but where they’re right they may be getting it from a system prompt and in some cases are known to be e.g. Claude I was deliberately including that as a way to pass, because fixing this via system prompt best practices is fine
-
Comprehensive Survey of AI Prompting Techniques and Methods
By
–
Systematic Survey of Prompting Techniques: https://
arxiv.org/abs/2406.06608 [77-page PDF]
======
#AI #GenAI #GenerativeAI #PromptEngineering #RAG #LLMs -
Skills Required for Working with Generative AI Models
By
–
What does it take to work with Generative AI Models >> https://
buff.ly/3DzqTY2 #AI #GenAI #ArtificialIntelligence #AIModels @IIoT_World @CRudinschi via @fogoros -
DeepSeek V-3: China Leads Open-Source AI
By
–
And so, China can no longer be ignored. DeepSeek V-3 is a new open-source model (635 billion parameters!!!) that outperforms most of GPT-4-O's benchmarks while costing 10 times less in API fees. For several years now, there have been excellent…
-
Dynamic AI Conversations: Why Users Aren’t Leveraging Toggle Features
By
–
For months now, we’ve been able to hold dynamic conversations with AI: interrupt, redirect, share live screens, selfie cameras, and more. And yet, most people have not adjusted their behavior to leverage these 'Toggle with AI' capabilities. I don't mean conversation turns (like
-
Why models don’t know their own release version
By
–
A model can’t know its own release version because it’s usually only decided that a trained model *should* be a release version once it’s fully post-trained, red-teamed, etc. Human demonstrations are necessarily older. Claude I assume would learn it in RLAIF.
-
Comment on system prompt and post-training practicality
By
–
Yeah sorry, was unclear this is coming from the system prompt — the reason I ask this is because it’s impractical to teach it in post-training. Added a comment to the thread: