Matt Silverlock

@elithrar.bsky.social

“Who do we say the rules are for?” “Other people.” • VP of Product: Databases & Storage @cloudflare • https://github.com/elithrar • https://twitter.com/elithrar

I wanted a way to benchmark a bunch of LLMs from the CLI. Wrapped @simonwillison.net’s llm library + had it ingest a config file specifying the models you want. It'll run them async (if the plugin supports it) and write the results out to JSON so you can review/eval/process.

Bild

When one of the PMs on the team *builds a macOS app* that uses Workers AI to auto-transcribe notes from any system process, summarize them, and do it all privately within your own Cloudflare account 😎

Bild

Case in point: I like AI for prototyping, but… are we headed towards a monoculture because that’s all our tools support? Do other libraries stand a chance? Do we get to try out new ideas? I’m hoping the next big advance in LLMs enables more real-time knowledge (that isn’t just function calling).

Bild
Matt Silverlock@elithrar.bsky.social · 2y ago

How do we experiment with new ideas, frameworks & ship new APIs as the reliance on LLMs increases? Specifically: the current gap between training data (April 2024 for Claude!) means that there’s far more friction for users to try something new or different.

How do we experiment with new ideas, frameworks & ship new APIs as the reliance on LLMs increases? Specifically: the current gap between training data (April 2024 for Claude!) means that there’s far more friction for users to try something new or different.

tried writing this blog 3 times but it’s really boring, so here’s the short version: React won. Every mainstream f/w now implements its ideas, and developed their own ecosystems. The ones that didn’t, lost and died. This implies there’s no _strong_ reason to not pick one of the other winners.

Being a good writer has always been valuable, but in an era of bland AI slop I suspect that being able to write with an authentic, human voice is effectively becoming a super power

Just added the (brand new!) support for Llama 3.3 70B in WorkersAI to llm-cloudflare $ llm install llm-cloudflare $ llm -m "@cf/meta/llama-3.3-70b-instruct-fp8-fast" <PROMPT>

Bild
Matt Silverlock@elithrar.bsky.social · 2y ago

Built a plugin for @simonwillison.net’s llm CLI: allowing you to call any Workers AI model directly from the command line. $ llm install llm-cloudflare $ llm keys set cloudflare $ llm -m "@cf/meta/llama-3.1-8b-instruct" "Write a Cloudflare Worker in ESM that returns JSON."