31–40 of 65 posts
How does this part work? "The LLM outputs compact code (~50 tokens) instead of raw Excalidraw JSON (~5,000 tokens)." I see on the left that the LLM is outputting some instructions to add nodes and edges to the diagram. But what is interpreting those commands and turning them into an Excalidraw file?
The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed
If you do a Google image search for "OAuth 2.0 PKCE sequence diagram" you get good results also. Maybe if you ask for something more esoteric this becomes valuable? Of course, that also makes hallucinations more likely.
The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed
I'm very surprised by this, in my tests E2B has very limited general knowledge.
The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed
May I ask what setup you used to run it on your phone and if it's satisfactory (it sounds like it)?
I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an engineering proposal I just finished. In past years I would have fumbled around with Visio forever and the result would have been worse.
And yet people here insist that the height of an llm is not being above to draw a pelican or count letters in a word
The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed
> It gave me basically the same as Gemini or ChatGPT would do I'm very surprised by this, in my tests E2B has very limited general knowledge.
Earlier quoted context omitted.
Did not know that. That sounds extraordinary wasteful, there must be a file hash based method that would allow sharing such files between domains.
it's a security feature. otherwise my malicious site could check for cdn.sensitivephotoswebsite.com and blackmail you if it was cached already
I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an engineering proposal I just finished. In past years I would have fumbled around with Visio forever and the result would have been worse.
I just ask Claude code for mermaid to visualize any topic I'm discussing.