HN user

fosterfriends

591 karma
Posts53
Comments115
View on HN
cursor.com 7mo ago

Graphite is joining Cursor

fosterfriends
276pts253
www.macrumors.com 8mo ago

Samsung Follows Apple's AI Strategy with Perplexity-Powered Bixby

fosterfriends
2pts0
www.theverge.com 1y ago

TSMC announces $100B investment in US chipmaking

fosterfriends
5pts2
smalldiffs.gmfoster.com 1y ago

Takehomes and Algos Are Both Evil – and Other Lessons from 1000 SWE Interviews

fosterfriends
3pts0
smalldiffs.gmfoster.com 1y ago

What Happened to Lightweight Desktop Apps? History of Electron's Rise

fosterfriends
2pts1
smalldiffs.gmfoster.com 1y ago

Are you having any fun?

fosterfriends
5pts0
smalldiffs.gmfoster.com 1y ago

The Most Important Part of Engineering Management: Context

fosterfriends
1pts0
smalldiffs.gmfoster.com 1y ago

The Bryan Johnson Approach to Eng Productivity

fosterfriends
2pts0
smalldiffs.gmfoster.com 1y ago

How to Be a 10x Engineer: Execute in an Extreme Straight-Line

fosterfriends
5pts21
smalldiffs.gmfoster.com 1y ago

Will AI Transform or Threaten the Per-Seat SaaS Model?

fosterfriends
1pts1
graphite.dev 1y ago

Onboarding roulette: deleting our employee accounts daily

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

Should SaaS startups offer on-prem?

fosterfriends
3pts3
gregmfoster.substack.com 1y ago

Atlassian, from the Perspective of a Younger Developer

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

ChatGPT's "Work With Apps": Slowly deprecating code editors

fosterfriends
2pts0
gregmfoster.substack.com 1y ago

Biographical vs. Aspirational Startup Values

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

Stacking and Agentic PRs Go Hand in Hand

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

Amazon Q and Gitlab Duo: Still Missing a Killer Differentiator

fosterfriends
1pts0
www.theverge.com 1y ago

iOS 18.2 is rolling out now, adding ChatGPT integration and more Apple Intellige

fosterfriends
4pts0
gregmfoster.substack.com 1y ago

Pricing Intelligence: Is ChatGPT Pro too expensive for developers?

fosterfriends
2pts0
gregmfoster.substack.com 1y ago

Git is bad. Here's how I'd make it better

fosterfriends
1pts5
gregmfoster.substack.com 1y ago

AI in dev tools, late 2024: where we are and where we might be headed

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

Designing a Startup Infra Team

fosterfriends
2pts0
gregmfoster.substack.com 1y ago

Becoming a lead at a startup – from the audience to the stage

fosterfriends
1pts0
gregmfoster.substack.com 1y ago

Friends and Family Email Lists

fosterfriends
1pts0
www.anthropic.com 1y ago

Graphite speeds up code review by 40x with Claude

fosterfriends
4pts1
graphite.dev 1y ago

AI code generation will remain fragmented

fosterfriends
1pts0
planetscale.com 1y ago

PlanetScale Updated to Plaintext Website

fosterfriends
17pts4
graphite.dev 2y ago

Google Does Code Review

fosterfriends
3pts0
graphite.dev 2y ago

Do you ever outgrow GitHub?

fosterfriends
1pts2
graphite.dev 2y ago

From the 80s to 2024 – how CI tests were invented and optimized

fosterfriends
2pts0

I really like all these ideas - very similar to what we discuss internally! We need to iterate our way there, but working with Cursor makes some of these visions much more possible

(Re-sharing some thoughts I posted on other HN thread)

Hi all! Graphite cofounder Greg here. I’ve been asked a few times so far why we decided to join.

Personally, I work on Graphite for two reasons. 1) I love working with kind, smart, intense teammates. I want to be surrounded by folks who I look up to and who energize me. 2) I want to build bleeding-edge dev tools that move the whole industry forward. I have so much respect for all y’all across the world, and nothing makes me happier than getting to create better tooling for y’all to engineer with. Graphite is very much the combination of these two passions: human collaboration and dev tools.

Joining Cursor accelerates both these goals. I get to work with the same team I love, a new bunch of wonderful people, and get to keep recruiting as fast as possible. I also get to keep shipping amazing code collaboration tooling to the industry - but now with more resourcing and expertise. We get to be more ambitious with our visions and timelines, and pull the future forward.

I wouldn’t do this if I didn’t think the Cursor team weren’t standup people with high character and kindness. I wouldn’t do this if I thought it meant compromising our vision of building a better generation of code collaboration tooling. I wouldn’t do it if I thought it wouldn’t be insanely fun and exciting. But it seems to be all those things, so we’re plunging forward with excitement and open hearts!

Heard on the worry, but I can confirm Graphite isn’t going anywhere. We're doubling down on building the best workflow, now with more resourcing than ever before!

Hi all! Graphite cofounder Greg here - happy to help answer questions. To preempt one: I’ve been asked a few times so far why we decided to join.

Personally, I work on Graphite for two reasons. 1) I love working with kind, smart, intense teammates. I want to be surrounded by folks who I look up to and who energize me. 2) I want to build bleeding-edge dev tools that move the whole industry forward. I have so much respect for all y’all across the world, and nothing makes me happier than getting to create better tooling for y’all to engineer with. Graphite is very much the combination of these two passions: human collaboration and dev tools.

Joining Cursor accelerates both these goals. I get to work with the same team I love, a new bunch of wonderful people, and get to keep recruiting as fast as possible. I also get to keep shipping amazing code collaboration tooling to the industry - but now with more resourcing and expertise. We get to be more ambitious with our visions and timelines, and pull the future forward.

I wouldn’t do this if I didn’t think the Cursor team weren’t standup people with high character and kindness. I wouldn’t do this if I thought it meant compromising our vision of building a better generation of code collaboration tooling. I wouldn’t do it if I thought it wouldn’t be insanely fun and exciting. But it seems to be all those things, so we’re plunging forward with excitement and open hearts!

Google Antigravity 8 months ago

Anyone else getting this error: "Agent execution terminated due to model provider overload. Please try again later."

Gemini 3 8 months ago

Thrilled to see the cost is competitive with Anthropic.

Gemini 3 8 months ago

Gemini 3 and 3 pro are good bit cheaper than Sonnet 4.5 as well. Big fan

You can code PRs fast, but CI, review, merge, deployment, monitoring, all takes just as long as it did before. The inner loop is shrinking; the outer loop is the real bottleneck

Graphite | Mid-level & Senior Software Engineers| New York, NY in our Soho Headquarters | https://graphite.dev

We’re building Graphite to help high-performing engineering teams run faster, cleaner code reviews. Our product is already used by some of the world’s best developers, and we’re just getting started! We're hiring experienced engineers across the stack, are are looking for people who:

-Care deeply about code quality, system design, and scaling software responsibly

-Have a strong product sense and enjoy collaborating closely with design & product teams

-Have experience with AI-driven workflows, prompt engineering, or interest in developer tooling is a plus

-Are product-driven and quality-obsessed; we ship thoughtfully and often

We've recently raised a $52m Series B by Accel, A16z, & others, and have big goals this year.

The hiring process: quick intro call, 2 technical interviews, & an onsite interview, followed by offer!

If you are someone who wants to work on meaningful problems, values clean code and thoughtful systems, & loves building tools for other engineers, we'd love to chat with you!

You can apply directly on our careers page(https://graphite.dev/careers#positions) or email sam@graphite.dev with the subject title: "Thank you for stacking with us) with a copy of your CV.

Recruiters: appreciate your hustle, but we’re only hiring through direct applications.

Fascinating - are you imagining a sort of adversarial AI situation, where one LLM bot writes the PRs, and a different one reviews them, leading to an organically improving codebase? Kind of a cool idea.

I really like the general take that LLMs scanning PRs is simply "zero config CI." We already have a great paradigm for this; we don't need to reinvent a new category. In that light, we can weigh its value more as a fuzzy linter, rather than a be-all-end-all.