Automorphic (h/ai) retweetledi
Automorphic (h/ai)
57 posts
Automorphic (h/ai)
@AutomorphicAI
Infuse knowledge into language models with just 10 samples
Katılım Haziran 2023
8 Takip Edilen200 Takipçiler
We at Automorphic are committed to building AI that improves lives & unlocks a better future for humanity. We are proud to sign the Open Letter: Build AI for a Better Future along with @SVAngel, @OpenAI, @Meta, @Google, @Microsoft & many others!
Ron Conway@RonConway
We all share responsibility for building AI that improves lives & unlocks a better future for humanity. @SVAngel makes this pledge, and we are proud to initiate this Open Letter: Build AI for a Better Future. Please join @OpenAI, @Meta, @Google, @YCombinator, @HuggingFace, @Databricks, @MistralAI, @elevenlabs, @Salesforce, @Microsoft & others in signing today! Sign here: openletter.svangel.com
English
Automorphic (h/ai) retweetledi
@tnachen @EssenceVenture @spirinus @nvidia @tristanzajonc @continual_ai @AutomorphicAI Finally, the Automorphic team gave us a rundown of all of the valuable fine-tuning tooling they've built to infuse domain knowledge in models (4/5)
English
Automorphic (h/ai) retweetledi
Automorphic lets you fine tune LLMs incrementally, and that means you can evolve them much faster. It's like programming in a repl.
ycombinator.com/launches/JOw-a…
English
Even ChatGPT is still able to be fooled into breaking its boundaries after all this time and billions in training. Do you really trust your own custom LLM to not say/do something bad to your customers?
English
We just did our launch YC and would love your support: ycombinator.com/launches/JOw-a…
If you or anyone in your network is interested in replacing OpenAI / implementing custom LLMs, feel free to schedule a demo: calendly.com/automorphic or reach out at founders@automorphic.ai
English
@Chrisprucha Building A(G)I... more specifically, eliminating LLM hallucinations
English
if you're e/acc and building, reply here and I'll follow you ❤️🔥
English
@amasad If you need structured output, you can do the same with our API and get 100% reliability
github.com/automorphic-ai…
English
A buried lede in this library is an elegant and generic “function calls” that works with any LLM and does not rely on OpenAI’s native feature. You just pass it an API schema and a way to handle calls. Even more impressive it ships with a simple interpreter so no eval() calls.
Anders Hejlsberg@ahejlsberg
Today we’re releasing TypeChat (microsoft.github.io/TypeChat/blog/…), an open source project that uses AI to bridge between natural language and application schema and APIs. It uses TypeScript in novel and interesting ways. Check it out and let us know what you think. @TypeScript
English
Getting into AI is like joining the mob. You are there for life, you can never leave. There is no such thing as “ex AI”.
English
I hate to admit it, but Pi (the overly friendly LLM) is growing on me.
English
@dflieb Looks like our unstructured to structured JSON, regex, or context free grammar output converter, Trex🦖
English
San Francisco is a magical place.
Mission Dolores, San Francisco 🇺🇸 English
@creatine_cycle Effective Accelerationism: effectiveaccelerationism.substack.com/p/repost-effec…
English
@katmhuang We don't, think we need to upgrade to Automorphic Aegis now
English
going to staples can you check if we still have any norton antivirus left in the fridge
English
@shl Which is why we just launched our unstructured data to structured JSON, regex, or other cfg output converter
English
Launching is like walking. You keep doing it until you get where you want.
English