More expensive currently. I expect that to shift within a few years.
@mattshumer_
-
Scalable Self-Play with LLMs: Current Research and New Approaches
By
–
What's the closest researchers have gotten to scalable self-play w/ LLMs? Had an idea I think is unique and easily implementable, curious if there is anything I should take a look at.
-
Fine-tuning Shifting to Many-shot Prompting in Coming Years
By
–
I’ve been saying this for a while now. Over the next couple of years, *most* fine-tuning work will become many-shot prompting.
-
LLaMA 3 Context Window Extended to 1 Million Tokens
By
–
Thanks @KalleyHuang and @theinformation for writing about my work extending LLaMA 3’s context window. And shoutout to @winglian @nisten and @markatgradient who took this even further and scaled LLaMA to 1M tokens. Article in next tweet:
-
AI Agent Version Gains Rapid Follower Growth
By
–
wtf, @aimattshumer (the AI version of me) is growing followers fast going to sleep, excited to see where it’s at in the morning
-
Would You Follow an AI-Run X Account?
By
–
If I were to create an X account run entirely by AI, would you follow?
-
Running Standard LLM Benchmarks: The Easiest Approach
By
–
What’s the easiest way to run the standard set of LLM benchmarks?
-
AI Summarizer Bot Saves Time via Text Messages
By
–
— Matt Shumer (@mattshumer_) 30 avril 2024
I made myself an insanely useful AI summarizer bot. It lives in my text messages. I just send it a link to an article, video, etc., and it texts me back a fantastic summary, in seconds. This is going to be a massive time-saver.
-
$200 Bounty: Custom Collator for Unsloth AI Completions
By
–
I'll give $200 to the first person who writes a fully working custom collator for @UnslothAI that allows for only training on completions.