brianjking

Seeing SSL errors trying to load the site.

Okay, this is just nuts at this point.

lol, clearly doesn't seem to be.

No, Poe uses APIs to the foundation model providers running inference in the cloud.

Email them, they applied it for me.

cpeffer - What about sites requiring auth? (IE: Confluence, staging environments, etc.)

I'm honestly really impressed.

As I'm trying to work on some pricing info for PGVector - can you share some more info about the hacker news posts you've embedded?

* Which embedding model? (or number of dimensions) * When you say 6 million posts - it's just the URL of the post, title, and author, or do you mean you've also embedded the linked URL (be it HN or elsewhere)?

Cheers!

This and Co:here's Compass embeddings model from yesterday are leaving me HIGHLY excited!

Great work, thank you, Simon.

Have you noticed GPT-4 Vision do weird selections of dates for 2019? In doing some processing of some data for work, I ended up switching to textract and then passing the OCR'ed text to GPT-4 and mapping to a Pydantic schema due to this issue.

curl https://api.openai.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -d '{ "model": "gpt-4-turbo", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What'\''s in this image?" }, { "type": "image_url", "image_url": { "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gf..." } } ] } ], "max_tokens": 300 }'

No, but you can use the API via Postman.

Providing examples generally helps me. Have you checked out the Instructor library too?

^ This.

I've found success generally better with Textract and then passing the OCR'ed text to OpenAI and using Pydantic to get it structured.

Congrats to Beeper, but I think that means I'll end up having to pay $25 or something to keep using it.

How will this differ from https://texts.com/ which is also owned by Automattic?

Yes, welcome to imposter syndrome.

Agreed. Opus definitely has taken most of my usage as of late.

You can opt out of training while keeping history turned on in the privacy center at https://privacy.openai.com/policies.

This was previously a Google Form, they've since migrated into a dashboard with actual confirmation.

Yeah, Opus has entirely taken over any code specific use for me over ChatGPT 4 or OpenAI GPT-4 API.

Once Opus has the ability to run a code interpreter, it'll really be an exciting time.

Claude 3, easily. Especially for code. Multimodal capabilities are incredibly impressive there too as well.

This is so absurd. If this is legal, it surely shouldn't be.

Remote work works.

Will the new Beeper app gain support for Fitbit as the "Messaging" app? Before I could select Beeper, Google Messages, or WhatsApp. The new app isn't recognized by Fitbit as an SMS messaging app.

Is there still plans for supporting multiple G Apps accounts?

This is a fantastic read.

How LastPass / LogMeIn is still a company at this point is so beyond me.

lol, which time? LastPass is so very incompetent.

Yes.

This is going to be really, really, really nice. Signed up for your waitlist. Cheers!

How do you see the Replicate vs Modal.com overlap?

Would be curious to see how this compares to Modal.com too.

100%, I can't even use Imagen despite being an early tester of Vertex.

Archive link: https://archive.is/9nDyx