Patrick DeVivo

software engineer in NYC. prev and Now @powersetres.

[Patrick DeVivo @patrickdevivo]

switched from Claude Code to Codex CLI today and am experiencing this in real time. I can’t articulate exactly why…it’s just better

Less sycophantic? Feels more comprehensive? 5.5 seems to just miss fewer things

[Nick Schrock @schrockn]

Underreported story in AI Eng: Just how much better it is to work with gpt 5.5 than Opus 4.8. It's smarter *and* has a decisive speed advantage. The speed difference also underrated.

[Powerset Research @PowersetRes]

The best recruiting signal is often sitting in public GitHub data.

Today, we’re open sourcing the data layer we use to help founders recruit exceptional engineers.

https://t.co/yaZwMUSmkS

[Patrick DeVivo @patrickdevivo]

e.g. don't spend cycles on frontend code, spend time getting the agent connected to a design system, following best practices, and self-verifying its own code changes.

the work is now building and operating the machine that ships and maintains code, not the code itself

[Patrick DeVivo @patrickdevivo]

the job of software engineer is so clearly no longer about directly managing code, but managing the systems and rails for AI tools to ship the best possible codel, given the domain and its constraints

[Jake Zeller @jake_zeller]

1/ Applications are now open for Powerset Cohort 4, where top founders get their own $ 1M+ fund for angel investing. Last year, Anton Osika (Lovable) and other elite founders joined Cohort 3. Our founders have deployed $ 20M+ so far and are outperforming top VCs.

[Patrick DeVivo @patrickdevivo]

I think there are interesting use cases for sandboxes that have nothing to do with AI code execution.

If you can isolate tenants and pin them to their own compute, that’s a pretty powerful primitive for multi-tenant software generally.

CI/CD systems, per-tenant queries with variable compute/memory, third-party plugin systems, user-defined logic, etc.

Cool to see AI infra make infra better for non-AI products too.

[Patrick DeVivo @patrickdevivo]

@thdxr I now ship stuff that pre-AI would've been sidelined for more important features and never made it out of the backlog, but now are a no brainer to implement. The long tail of small features and easter eggs: general polish that ends up raising the resulting product quality

[Patrick DeVivo @patrickdevivo]

@penberg very cool - could be fun to test it on @archildata

[Patrick DeVivo @patrickdevivo]

@rauchg long running background workers!

[Patrick DeVivo @patrickdevivo]

@SemiAnalysis_ we built a tracker of coding agent commit counts on public GitHub projects: https://t.co/HeGXIBh9Gc

[Patrick DeVivo @patrickdevivo]

7/ Instead of a human prompting specific features and fixes to move a codebase forward, do we end up in an even more declarative/spec-driven world, where human changes are text updates to a CLAUDE.md spec and agents continuously work to reconcile to a final state?

[Patrick DeVivo @patrickdevivo]

1/ If history is any guide, I think the end state of agentic coding is something far more declarative than imperative (relative to where we are today). We’ve headed far in that direction, but there’s probably more to go…

[Patrick DeVivo @patrickdevivo]

6/ I think there’s more to climb on the “declarative-ness” ladder though. Especially when it comes to on-going maintenance and day two development.

[Patrick DeVivo @patrickdevivo]

@DoltHub 🚀

[Paul Copplestone - e/postgres @kiwicopple]

supabase open source metrics:

[Patrick DeVivo @patrickdevivo]

@bcherny 🚀