Patrick DeVivo

969 posts

Patrick DeVivo

Patrick DeVivo

@patrickdevivo

software engineer in NYC. prev https://t.co/Bx70AikU07 and https://t.co/ZTUpgwRJgC. Now @powersetres.

New York Katılım Kasım 2007
1.2K Takip Edilen862 Takipçiler
Patrick DeVivo
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
English
0
0
0
45
dax
dax@thdxr·
i really don't care about using AI to ship more stuff it's really hard to come up with stuff worth shipping i want to ship the same amount of stuff with higher quality both in product and code
English
116
135
2.5K
67.5K
Pekka Enberg
Pekka Enberg@penberg·
Turso 0.5.0 is now out! ⚡ Concurrent writes is now beta 🔍 Full-text search with Tantivy 🔒 STRICT mode stable + user-defined types Big thanks to the 50+ people who contributed over 3,000 commits into this release! turso.tech/blog/turso-0.5…
English
7
23
178
39.1K
Guillermo Rauch
Guillermo Rauch@rauchg·
What service should we build next, with deep care and investment into its security, availability, and durability?
Guillermo Rauch@rauchg

Queues are one of the most requested services since I started Vercel. They're now here. It's just two APIs: 𝚜𝚎𝚗𝚍 and 𝚑𝚊𝚗𝚍𝚕𝚎𝙲𝚊𝚕𝚕𝚋𝚊𝚌𝚔 😌. The use-cases are basically infinite. Notably: queues can make agents and AI apps reliable. Quality and reliability are top of mind for everyone now, including our own team. We went through 3 iterations of the infrastructure while in private beta, and we're excited for you to build 'unbreakable software' with it.

English
145
3
272
93.4K
SemiAnalysis
SemiAnalysis@SemiAnalysis_·
4% of GitHub public commits are being authored by Claude Code right now. At the current trajectory, we believe that Claude Code will be 20%+ of all daily commits by the end of 2026. While you blinked, AI consumed all of software development.
SemiAnalysis tweet media
English
169
372
3K
611.4K
Patrick DeVivo
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?
English
0
0
0
25
Patrick DeVivo
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.
English
1
0
1
33
Patrick DeVivo
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…
English
1
0
1
43
Boris Cherny
Boris Cherny@bcherny·
We shipped Claude Code as a research preview a year ago today. Developers have used it to build weekend projects, ship production apps, write code at the world's largest companies, and help plan a Mars rover drive. We built it, and you showed us what it was for.
English
346
320
7.8K
333.8K
Patrick DeVivo
Patrick DeVivo@patrickdevivo·
@nateberkopec Claude Code is my default BI tool now - connects to a database and generates charts on the fly. throwaway python for generating matplotlib images or interactive html charts with vega-lite. Ad hoc data exploration is so much easier…
English
0
0
0
286
Nate Berkopec
Nate Berkopec@nateberkopec·
You are probably not using LLMs enough to generate non-code artifacts. "Review this PR and then generate an interactive HTML website to explain it. Turn this state machine into a mermaid diagram. Generate a 10,000 word deep research report on the state of the art of CSRF protection."
English
17
10
233
16.5K
Patrick DeVivo retweetledi
Wes McKinney
Wes McKinney@wesmckinn·
Just released my next-generation agent session viewer with analytics dashboard (Go + Svelte). A much evolved version of wesm/agent-session-viewer which is now deprecated: agentsview.io
Wes McKinney tweet media
English
8
20
163
14.1K
will brown
will brown@willccbb·
duuuude don't train on claude outputs, not cool. train on public github repos instead, which are fair game and definitely not claude outputs
English
36
13
1.1K
63.2K
Patrick DeVivo retweetledi
Powerset Research
Powerset Research@PowersetRes·
We replicated the @SemiAnalysis_ estimate that ~4% of public GitHub commits are being authored by Claude Code. Moreover, this figure is growing exponentially.
Powerset Research tweet media
English
4
5
17
3.9K
Patrick DeVivo
Patrick DeVivo@patrickdevivo·
@ivanburazin I also think AI makes it much easier for teams to self-host in the long term. Smaller teams can manage more infra ops with agents running around handling infra as code, setting up observability, upgrades, etc
English
1
0
1
81
Ivan Burazin
Ivan Burazin@ivanburazin·
Pre AI, developers wanted open source so they could self host and review code. Today everyone just wants an API key. People are moving way too fast to care about running things themselves.
English
14
0
29
2.9K

Keşfet

@thdxr @penberg @archildata @rauchg @SemiAnalysis_ @DoltHub @bcherny @ivanburazin