pheeney

Is any of it open source? What tools for the CSV? I’d like to build a dashboard of my cycling rides?

Is this open source? Or would you be willing to share the prompt of how you accomplished the faithful representation of content? I’m curious what approach you took that sets it apart from the tools that you felt had failed. I didn’t watch the original video but the article looks well formatted.

I'd guess to add something like RSC or more integrated data loading. Seems like we have to wait until October to find out more, but hopefully they drop more information earlier.

I was able to get it working and it seemed fast enough. However I don't have any local databases of similar size to compare to.

ssh -F ssh.config -L 4213:localhost:4213 dev 'DUCKDB_HTTPPORT=4213 ~/.duckdb/cli/latest/duckdb -ui'

What is the ideal use case for this? It looks to be 13.5x more expensive for a much smaller model.

DeepSeek R1 Pricing (per 1 million tokens)

    Input: $0.00135 × 1,000 = $1.35
    Output: $0.0054 × 1,000 = $5.40

Google Gemini 2.0 Flash Pricing (per 1 million tokens)

    Input: $0.10
    Output: $0.40

My ip is dynamic so it seems I would need to wrap it in a script that would handle opening and closing. I didn’t see any authentication built into the UI. Seems like a great local tool but harder to get right in production.

It looks like the port is configurable, so that should make it easier to avoid conflicts but I wonder how the performance would be impacted.

What is the best method for using the UI with a remote server that only has SSH access? The database is too large to rsync locally and seems risky to start opening ports?

I'd be curious too. It sounds like standard RAG, just in the opposite direction than usual. Summary > Facts > Vector DB > Facts + Source Documents to LLM which gets scored to confirm the facts. The source documents would need to be natural language though to work well with vector search right? Not sure how they would handle that part to ensure something like "Patient X was diagnosed with X in 2001" existed for the vector search to confirm it without using LLMs which could hallucinate at that step.

What models would you recommend for basic classification if you don't need a 24B parameter one?

Do you have to tip on the Walmart grocery delivery? I thought about signing up but the cost savings goes away if tipping is expected.

Same thing happens to me with Firefox on iOS.

I wonder how much they use their own products internally to speed up development and decisions.

What is the best provider for API use of llama frontier models considering pricing / reputation?

Is there a GitHub issue or discussion to subscribe for updates from the Remix team on this topic?