Akeem

@akeem

146 Following

53 Followers

Akeem pfp

I was 0 km away from today's mystery location 📍. Can you beat me?

0 reply

0 recast

0 reaction

Akeem pfp

0 reply

0 recast

1 reaction

Akeem pfp

yesterday I simplified something that should make back search a lot easier: deepgram diarizied data -> split by speaker with metadata -> vectorized -> into pgvector. I should now be able to do give me references Cosmos within this date range, and who did the mentions etc

0 reply

0 recast

0 reaction

Akeem pfp

with hours and hours of audio to process, Meridian is on the back of a lot of LLM work. Initially I wanted a tool to provide trend data and the newsletter is a tangible way for me to justify the work. Particularly because it provides value to people without having to do the work.

1 reply

0 recast

0 reaction

Akeem pfp

One of my goals for Meridian is to ensure that it feels as native to the internet as possible. This will evolve as needed to resonate with the audience of today and tomorrow. With yesterday's issue, I also published a companion playlist that you should checkout https://blog.getmeridian.io/p/playlist-eth-scaling-solutions-by-2026-btc-edges-toward-83k

0 reply

0 recast

0 reaction

Akeem pfp

with that said, feel free to sign up to https://www.getmeridian.io/

0 reply

0 recast

0 reaction

Akeem pfp

I asked claude 3.7 Sonnet to write me a prompt for gpt-4o for the speaker assignment and now I have something I can pass a transcript to ,it samples, and provides predictions of which speakers are which

1 reply

0 recast

0 reaction

Akeem pfp

We sort of do this heuristic in our head of eliminating who the speaker isn't each time we listen to a new podcast. Since we can give the model a fair bit of context it should be able to knock it all down

1 reply

0 recast

0 reaction

Akeem pfp

The context is in the conversation, and is an easy task for a human. For examples sake, we can say that introductions occur within the first few minutes of a podcast and the enrichment can occur

1 reply

0 recast

0 reaction

Akeem pfp

The last issue of the newsletter covered 22 podcasts, that is a pretty heavy time investment for each issue. So I decided to see how far I could get with some of the easily accessible models

1 reply

0 recast

0 reaction

Akeem pfp

transcribing podcast in generally a starting point, base transcriptions can identify that several people are talking but not who they are. So enrichment is needed

1 reply

0 recast

0 reaction

Akeem pfp

working on Meridian, my newsletter that aggregates insights from crypto podcast, I leverage LLMs regularly as leverage. Sometimes to eliminate things that would otherwise be a pain in the neck to write.

1 reply

0 recast

0 reaction

Akeem pfp

swag acquisition opportunities for those not able to make it in person?

0 reply

0 recast

0 reaction

Akeem pfp

the leaning tower of ... pizza boxes, sorry I couldn't help myself

1 reply

0 recast

2 reactions

Akeem pfp

this should be posted on the door of any startup that has reached the size of needing a door

0 reply

0 recast

0 reaction

Akeem pfp

The newsletter is spinning up, get aggregate insights from podcast in the crypto space in your inbox 3 times a week! https://getmeridian.io . Sign up today!

0 reply

0 recast

2 reactions

Akeem pfp

Last week, I mentioned starting a newsletter. Here is a link to the sign up page www.getmeridian.io , the first issue should go out tomorrow :-)

0 reply

0 recast

0 reaction

Akeem pfp

while exploring something that I wanted for myself, i've stumbled into a crypto newsletter. Over the coming days i'll think through how to use farcaster as a starting point

0 reply

0 recast

0 reaction

Infinex pfp

Based community. Based game 🔵 Claim 10 GP and win up to 1,000,000 Governance Points (GP) GP will be sent to your wallet, and can be migrated to your Infinex Account soon. https://farcaster-memecrash.infinex.xyz/gppromo

5 replies

381 recasts

406 reactions

Akeem pfp

I’m thinking through a use case that will require its own client. Is the idea that I would cast to my own channel to reduce noise for clients that can’t render my casts?

0 reply

0 recast

0 reaction