Richie Caputo

736 posts

Richie Caputo banner
Richie Caputo

Richie Caputo

@ARCaputo3

math and data guy

Miami, FL Katılım Eylül 2022
189 Takip Edilen130 Takipçiler
Mike Freedman
Mike Freedman@michaelfreedman·
Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL. Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database. There are two ways to use it: File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories. Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills. Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API. Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost. I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome. tigerfs.io
English
77
99
1.1K
116.4K
Mitchell Hashimoto
Mitchell Hashimoto@mitchellh·
Excited to share that I've joined Vercel's Board of Directors. Vercel is made up of builders and tastemakers that continually ship things that deeply impact how developers work: Next.js, AI SDK, v0, etc. I can't think of a more exciting place to be. Let's fucking ship. ▲ My relationship with Vercel goes back to the earliest days. HashiCorp was an early adopter of NextJS and Vercel (~10 years ago!) and it remains my default tech stack and deployment platform to this day. Ghostty's website is all on Vercel, too! Beyond that, I've been continually impressed with the teams relentless focus on shipping meaningful software. And importantly, software that has incredible taste. Now we are in the age of agentic software development. Vercel is building agentic infrastructure that I think every app and agent will need (I certainly need it!) and I can't think of a more exciting place to be. Huge thanks to @rauchg , Jeanne, Marten, @cramforce, @tomocchino and the entire Vercel team for the warm welcome. Time to work.
Mitchell Hashimoto tweet media
English
219
85
2.9K
587K
kache
kache@yacineMTB·
nano banana honestly kind of sucks
English
40
0
115
9.1K
Richie Caputo
Richie Caputo@ARCaputo3·
@georgecurtiss Schema and data living together is a convenient paradigm for LLMs. They can both evolve together an you don’t need to be very opinionated a head of time
English
0
0
1
20
George
George@georgecurtiss·
almost all the data you deal with is a graph... so why are you using a relational database?
English
12
0
21
3.5K
Richie Caputo
Richie Caputo@ARCaputo3·
@ah20im Similar sdk harness to Claude agent sdk for general purpose tasks
English
0
0
0
35
Ahmed
Ahmed@ah20im·
What would you like to see in Codex?
English
252
1
160
27.6K
Richie Caputo
Richie Caputo@ARCaputo3·
@IndraVahan I am convinced anything past 1m rows requires vectors and even then you should still use vectors + tsvector or bm25
English
0
0
1
92
Richie Caputo
Richie Caputo@ARCaputo3·
@bcardarella Can confirm, but typically they are sourcing said deals too so not entirely grift
English
0
0
1
33
Brian Cardarella
Brian Cardarella@bcardarella·
A friend in the VC/PE space told me there is an entire cottage industry of grifters that will analyze VC portolios to see if they have any gaps in market penetration then pitch on that gap because the investors have FOMO. Is this true, any verifiable evidence?
English
1
0
0
570
Richie Caputo retweetledi
Ben Davis
Ben Davis@davis7·
The current "MCP is dead discourse" is my current favorite example of the really annoying "simplicity" brainrot that's been plaguing tech for a while On paper "just use a cli agents already know bash" sounds really good. It makes sense and is true, but it misses the bigger picture: > how do they know about the commands + their shape? > just put it in your agents md file or make a skill > ok, so then what happens if the cli's shape changes > well then u just update the markdown file > fine let's pretend people will actually do that (they will not) and this actually works, how are you going to scope authentication and authorization? > use the cli auth tools like what AWS has > ok so we need eng's or agents to be manually making sure every project switches the auth to the correct scopes for each project so that prod can't get vibe killed and then to connect to our internal services over cli in cloud agents we need to run basic agents in sandboxes now b/c we're not using mcp and... You get the point. It sounds really simple, and it is in the toy case, but in the real world an external API gated through MCP is actually way simpler, more secure, and manageable in a lot of cases. This post & article from @GergelyOrosz is a very good example: x.com/GergelyOrosz/s… It's the same thing with the $5 VPS or htmx or postgres or whatever other "simple" enlightened solution that works great in dumb indie hacker demos while making zero sense in the real world. I hate to break it to you guys, but there's no conspiracy. If modern tech solutions really were over complex slop do u really think these companies wouldn't take the free win to just do it the "simple" way? There are tons of problems with the tech, but it exists for a reason. I like CLIs a lot, and in a lot of cases skills make sense, clis make sense, etc. There are a lot of ways to do things, and they all solve different problems. But no, MCP is not dead. It or something like it isn't going anywhere. And there are a lot of good new ideas of how to make it better! Dumping an MCP with 60+ random tools into context sucks I completely agree and needs to be fixed. A lot of the code run solutions are very compelling like @RhysSullivan 's executor, cloudflare's code mode, and others. There are ways to fix this, but a "god mode bash tool" isn't it.
English
54
30
366
53.5K
Brian Cardarella
Brian Cardarella@bcardarella·
Although... Zag? As in zig-zag
Nederlands
4
0
6
1.4K
Richie Caputo
Richie Caputo@ARCaputo3·
@bcardarella Damn beat me to it - how about calling it pig so you don’t need to use .zip?
English
0
0
0
42
@bluecow 🐮
@bluecow 🐮@BLUECOW009·
i want to refactor my entire codebase (website and API) to typescrypt, what are the chances that claude code will one shot it
English
20
0
14
2.1K
Richie Caputo retweetledi
Randy Olson
Randy Olson@randal_olson·
Summary of the MCP vs. CLI debate on X this week.
Randy Olson tweet media
English
39
70
778
44K
Richie Caputo
Richie Caputo@ARCaputo3·
@cjzafir @ud_ambwani It’s been solved with tool search months ago. MCP is actually back for that reason. JSON Schema beats CLI currently
English
1
0
5
514
CJ Zafir
CJ Zafir@cjzafir·
@ud_ambwani Unless we fix the context window issue, MCPs can't work. Its just a bloatware right now.
English
7
1
29
14.3K
CJ Zafir
CJ Zafir@cjzafir·
Some secrets: 1. Opus 4.5 > Opus 4.6 2. Codex 5.4 1M context is actually 512k 3. Qwen 3.5 is best OS model series (RN) 4. MCPs are dead 5. Openclaw was a prototype 6. Apple is the new NVIDIA 7. Perplexity is biggest grifter 8. Paper. design > figma 9. Ollama is just a crappy wrapper 10. Open source AI is ahead already.
English
154
125
2.4K
284K
Dwarkesh Patel
Dwarkesh Patel@dwarkesh_sp·
What should I ask Terence Tao?
English
529
74
3K
251.2K
Richie Caputo
Richie Caputo@ARCaputo3·
@leflushroyale @seatedro Agree - dbs need to be deterministic and reproducible. Vectors have point points but they work totally fine on 10m+ and better than text search alone (both is best)
English
0
0
1
71
Royal Flush
Royal Flush@leflushroyale·
@ARCaputo3 @seatedro It's not going to work reliably and will cost a small fortune to maintain. Vector bases are here to stay. LLMs, agentic or otherwise, are not the answer.
English
1
0
2
86
ronin
ronin@seatedro·
healthy dose of word salad and launch slop
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
20
6
494
42K