Generally I’d call that “conditioning the model”, which can take the form of either prompting or fine-tuning, but not sure if that’s exactly the right term. They’re two different techniques to make it respond how you want.
LLMS
-
Fine-tuning for AI Specialization and Performance
By
–
Not sure I understand fully re: alignment, but fine-tuning is usually the most performant way to specialize when you have the data for it.
-
Parameter Count Alone Cannot Measure LLM Quality
By
–
Comparing LLMs by param count is like comparing
– CPUs by megahertz in the 1990s
– cameras by megapixel in the 2000s
– phones by memory in the 2010s A primitive reductionism – true enough, but maxes out Then we pivot to fit-for-purpose measures.. That lead to enduring brands. -
GPT-3 Inference Non-Determinism at Temperature Zero Explained
By
–
An edge-case in GPT-3 with big implications: Inference is non-deterministic (even at temperature=0) when top-2 token probabilities are <1% different. So temperature=0 output is *very close* to deterministic, but actually isn't. Worth remembering.
-
The unique expertise of a Staff Prompt Engineer in LLMs
By
–
My goal is to do my job so well that I'm not just the first Staff Prompt Engineer, but the last. Most people don't have the time to learn what LLMs have taught me.
-
AI Today Podcast: Content Summarization and Sentiment Analysis Episode
By
–
In this @Cognilytica #AIToday #podcast episode 'Content Summarization and Analysis, Sentiment Analysis' from the AI Glossary Series, hosts @rschmelzer & @kath0134 define Content Summarization and #Analysis and #sentimentanalysis. Full episode: https://
cognilytica.com/2022/12/28/ai-
today-podcast-ai-glossary-series-content-summarization-and-analysis-sentiment-analysis/?utm_source=dlvr.it&utm_medium=twitter
…
#AI #nlp #ML -
Google’s PaLM: A 540B Parameter Language Model Explained
By
–
— AI Breakfast (@AiBreakfast) 29 décembre 2022
You've heard a lot about ChatGPT But in the next few weeks, you'll start to hear about another model that could be 3x more powerful than ChatGPT: PaLM Google's Pathways Language Model (PaLM) a 540-billion parameter model trained with the Pathways system Here's what we know
-
Get a complex SQL query from a simple natural request
By
–
— Defend Intelligence (Anis Ayari) (@DFintelligence) 29 décembre 2022
And the best part is that I can just ask it naturally, queries like "yes give me the table of all PlayStations sold in the Netherlands to customers who have a loyalty card". And poof, 30 minutes of work saved with the right SQL query.
-
Save 30 minutes of work by simply asking for an SQL query
By
–
Et le must c’est que je peux juste lui demander naturellement après, les requêtes genre “oui donne moi la table de toutes les PlayStations vendu aux paybas à des clients qui ont la carte de fidélité”. Et pouf 30min de taff d’économiser avec la requête sql qui va bien. pic.twitter.com/IgOK0sYZkt
— Defend Intelligence (Anis Ayari) (@DFintelligence) 29 décembre 2022And the best part is that I can just naturally ask it afterwards, queries like 'yes give me the table of all PlayStations sold to the Netherlands to customers who have a loyalty card'. And poof, 30 minutes of work saved with the right SQL query.
-
PaLM 540B Architecture Code Released Open Source
By
–
Mola, pero… ¿quién tiene capacidad de entrenar un PaLM de 540 billions (x3 el tamaño de GPT-3)? Aquí están compartiendo el código de la arquitectura y no un modelo pre-entrenado. Con lo que es un entrénalo-tú-mismo de ChatGPT.