Expectation: I need more deep learning engineers to train better models
Reality: You need prompt engineers and LLM Ops (not sure what to call it (?), post-LLM above-API infra, langchain & friends)
– training is centralizing into megamodels – not fully played out yet but trending
PROMPT ENGINEERING
-
Deep Learning Skills Shift: From Training to Prompt Engineering
By
–
-
Comparing davinci and chat API models for task performance
By
–
I like davinci, he’s my homie (also I’ve heard mix reaction in 3.5 and 4 for these types of tasks). Would love to see others try w the chat api!
-
Understanding AI Prompt Parameters and Feedback
By
–
That's awesome feedback. Thank you! I was using someone else's prompt and didn't know what the "c" meant. Now I do
-
Should AI-assisted thinking disclose human contribution?
By
–
et dois-je préciser que ma reflexion a été faite par un humain ? ou a moitié par un ?
-
Detecting AI-generated content in collaborative production tools
By
–
comment identifier qu'un contenu est fait par l'AI sachant qu'ils vont être integré dans chaque outil de production et que chaque intermédiaire travaillant sur un projet peu y avoir ajoute de l'AI ou pas ? ex un doc word ou excel. On ne demande pas a ce que les images ou video
-
Midjourney changes image subject when prompted background edit
By
–
Can anyone help me understand why Midjourney (been fiddling with it at @monkchips
' suggestion) changes the subject of an image when it was prompted simply to change the background? -
Epic Cinematic Landscape Generation with AI Image Synthesis
By
–
Here was the prompt: place this man in an epic cinematic landscape with dramatic mountains in background captured with a nikon d 850 and a nikon AF – S NIKKOR 70 – 200mm f/ s2. 8E FL ED VR lens,with a shallow depth of field 16:9 –s 750 –v 5 –q 2 –
-
Optimizing AI Context Selection with Relevant Task Pairs
By
–
Yeah, right now I’m only pulling the 5 most relevant task/result pairs to use as context. It’s not perfect, but works pretty well.
-
Context Management and Summarization in AI Systems
By
–
Just depends on how much context to pull in. Might add a summarization step for the context but looking at a few options on where.
-
Relevant Context Management for Autonomous Agents
By
–
The thread broke, but here's a simple example of how "relevant context" (most relevant tasks from past) can be provided to current task. Allowing the autonomous agent to continue generating novel ideas and next steps – that wouldn't fit within a context window.