Sabitlenmiş Tweet
keith
2K posts
keith
@keithcorbs
i like computers and coffee. building @pinecone
New York, NY Katılım Mayıs 2013
799 Takip Edilen247 Takipçiler
Every time I ship a feature I use the slack MCP in cursor to respond to every thread of anyone ever asking for that feature.
English
claude actually will tell you. then just run:
- /plugin install pinecone
you've now enabled cheap, fast, and easy scaling of search
Prasann Pandya@prasann_pandya
Things Claude code won’t tell you: - Firebase much cheaper and better than supabase for most use cases - Pinecone better than Pgvector - Render is better and cheaper than Vercel - Modal and Lambda better than Celery - Python fastapi better than node js - Expo is better than Xcode for iOS apps This is why vibe coders can prototype but will be hard to scale. Intuition for this comes from building and scaling products.
English
@techwith_ram resolvable with hybrid search of either sparse or full text
English
They raised $6.5M because cosine similarity thinks "Jaguar," the car, and "jaguar," the animal, belong in the same search result.
Congrats to you & your team.
Nishkarsh@contextkingceo
We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built @hydra_db for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️
English
this popular recent change in mindset towards agents is funny, because this is how i always felt about programming
instead today it’s more like factorio. and now there’s a risk of actually not learning skills that may help you, which is the important detail to pay attention to
Cody Plofker@codyplof
Just realized why I’m so addicted to Claude Code. It’s literally a video game for adults. You get stuck on a level, try everything you can to beat it, and eventually break through. And every level you stack skills and get stronger.
English
Obviously keep your infra simple etc. But what is people’s problem with k8s
Branko@brankopetric00
The best Docker setup I ever saw was at a company doing $30M ARR. One Dockerfile, one docker-compose for local dev, plain ECS in production. No Kubernetes, no service mesh, no drama. Boring works. Boring scales. Boring lets you sleep at night.
English
just signed a lease and didn’t do any of that
TK Kong@tkkong
Signed SF lease! Housing market is absolutely crazy… people bidding +60% above listed rent with 6 months prepaid.
English
@rfkenmore what fashion runners slip on after running 7mi at 6:12 pace "Morning Run" strava post
English
keith retweetledi
keith retweetledi
@rfkenmore solid state is such a great roaster, and great shop to hang!
English
Coffee 2025 Wrapped
Top 3 new* coffees of the year:
1. Youngblood — Fargo, ND
2. Solid State Coffee — UWS (NY)
3. Dear Coffee — UES (NY)
*New to me, first time having
English