I used E5-Large-V2 last year https://
til.simonwillison.net/llms/embed-par
agraphs
… Currently exploring @nomic 1.5: https://
github.com/simonw/llm-nom
ic-api-embed
…
TOOLS
-
E5-Large-V2 and Nomic 1.5 embedding models exploration
By
–
-
API Model Reliability and Self-Hosted AI Systems Concerns
By
–
Given how hard it is to iterate on, evaluate and build dependable systems on top of these models the idea that a model you've tuned an application for can have its API turned off at any moment is pretty nerve-wracking So I lean towards API models I can run myself if necessary
-
textract-cli: Simple Raw Text Extraction Without Table Processing
By
–
textract-cli currently does the simplest possible thing: it dumps out just the raw text, making no effort to decipher tables
-
Quantum World Visualization Through Midjourney Prompt Experimentation
By
–
I've been having fun with this simple Midjourney prompt: "the quantum world only exists when i see it." Every image generated is different but interesting. #quantum #midjourney
-
Build Complex AI Agents: Automate RFPs, Legal Docs, Security
By
–
Learn how to build complex AI agents in this FREE webinar! April 4 9:30 pm Discover how agents can help you with complex tasks like: – RFP creation
– creating legal docs
– answering security questions
– creating on-the-fly dashboards RSVP here: http://
eventbrite.com/e/ai-agents-us
e-generative-ai-to-automate-complex-tasks-tickets-867066357817?aff=oddtdtcreator
… -
LLMs Automating Well-Defined Tasks and Front-End Code
By
–
I suspect that well-defined tasks that can be posted to Fiverr or have a clear set of success conditions (e.g. make a custom WordPress plugin) are not far from being "automated" if that's how you think about it. Front-end code is already very LLM-suited!
-
AlphaTensor: Novel Matrix Multiplication Discovery and Security Automation
By
–
That said, here's an example of inventing new matrix multiplication (do your homework): https://
deepmind.google/discover/blog/
discovering-novel-algorithms-with-alphatensor/
… Plus, security vulnerabilities are found routinely (and by default) with automated tools on all serious projects. -
LLMs Tools and Data Structures Debate
By
–
These arguments are a strawman Filip; there are other tools for this and they work fine. (I wouldn't want to use a new data-structure that's not in a reliable library or shipped as standard.) These ignore main purpose that LLMs can be used for today…
-
Using LLMs to Simplify Complex Shell Commands
By
–
I also use LLMs for stupid shell commands that are not as intuitive as they should be. This also cuts down on looking up the man page or searching Stack Overflow.