Charlie Marketplace
@charliemktplace
🧵 How to think about building AI models (LLM Edition) How do LLMs work? 🏭 How do you scope a custom LLM? 📃 What are the tradeoffs between popular Foundational Models? 💱 Is Context enough? 📓 When is tuning worth it? ✍
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
[Instructions] + [Context] + [System Prompt] -> [Tuning filter] ->[Foundation Model] Instruction: summarize the main points of this article Context: the article System Prompt: behavior, censorship, capabilities (e.g., web browsing) Tuning Filter: specialize a model Foundational Model: GPT 3.5; Claude; Gemini; Llama-2
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
How do you scope a custom LLM? 📃 Have a specific goal: search? summarize? generate? Understand the resource constraints: proof of concept vs horizontal model (mixture of experts) vs vertical model (master many domains). The more ambitious the goal, the more likely you need tuning.
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
What are the tradeoffs between popular Foundational Models? 💱 In general, with enough context and tuning, models of similar size/complexity converge in quality. version control (deterministic testing), cost control, enterprise support, hosting, and avoiding getting rugged! LLMs = Chaotic = easy to break behavior.
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
Context is the easiest way to format a model's behavior. Simply *append* relevant information to every single user's request (i.e., exploit large context windows) Be careful: these can be *misleadingly* good in proof of concepts, but struggle to be aMaZinG in the wild https://warpcast.com/charliemktplace/0xbdce4dd1
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
When is tuning worth it? ✍ Tuning is *not* reducing model complexity. It's more like biasing some weights over others. You provide 50 -100+ pairs of custom input -> perfect dream output "squeeze" a foundation model to your preferred type of outputs for similar inputs. HUGE quality boosts for often < $100!
1 reply
0 recast
0 reaction
Charlie Marketplace
@charliemktplace
To summarize: customizing LLMs is becoming easier every day! The outstanding problems from my view are: - stochastic responses make testing hard - the best models are liable to rug you by fiddling with system prompts you can't control - open source models are still weak - Making great tuning data is a GRIND!!
0 reply
0 recast
0 reaction
