@HKrackDev
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
Building the future of code review @CodeRabbitAI Host of The Merge, Founder https://nitter.cf/t.co/PrQJ9avJtj Sharing what I learn from founders, engineers, and open-source builders
San Francisco, CA
Joined January 2025
- Tweets676
- Following453
- Followers533
- Likes1.2K
Pinned Tweet
Truth is, if your entire identity as a software engineer circles around writing high quality code you are rapidly becoming obsolete.
In the age of AI coding agents, pure implementation is becoming a cheap commodity - the only skill that actually commands a premium now is ruthless product sense & taste.
In my latest episode @kentcdodds explains why "Product Engineering" is the only career-saving pivot left for us developers who want to survive the AI arms race.
Our interns @xrhuang10, @_nikhilhooda and Utkarsh helped me organize this entire event, managing ppl, answering q's while somehow finding the time to hack themselves.
And then... independent judges picked them for 1st place 🏆
Couldn’t be more deserved. Absolute rockstars🤘👏🧡
1/ Yesterday we hosted @typesafeai at our @coderabbitai HQ for Jev's first ever hackathon!
160+ builders. ~4hrs of hacking. Expert judges, Incredible energy.
I also got to sit down with @allietheicon and talk about what Jev means for Coding, Software Development and the new paradigm shift you have to adapt when working with this new class of AI models.
She shared some really helpful tips and examples of how to best work with Jev - I'll try my best to summarize some of them in this thread⬇️
1/ Yesterday we hosted @typesafeai at our @coderabbitai HQ for Jev's first ever hackathon!
160+ builders. ~4hrs of hacking. Expert judges, Incredible energy.
I also got to sit down with @allietheicon and talk about what Jev means for Coding, Software Development and the new paradigm shift you have to adapt when working with this new class of AI models.
She shared some really helpful tips and examples of how to best work with Jev - I'll try my best to summarize some of them in this thread⬇️
3/ Speculative Prompting.
One of Jev's coolest patterns: ask questions before you even know you'll need the answers.
If 1 or 100 questions come back in roughly the same time, you can ask for every possible branch upfront. Then your code simply uses the answers it needs.
4/ More to come...
Stay tuned for the full episode.
We’ll dig into practical Jev examples, plus @allietheicon shares what it’s like working at a 20-person AI lab that suddenly blows up overnight.
Hendrik Krack retweeted
1/6 Twelve Judges Judging Jev:
field notes from Jevathon @coderabbitai in SF w/ @typesafeai & @AICollectiveCo.
Jev returns typed decisions, not text.
Wolves, dog sculptures, stroke triage & a GitHub roast, all w/ Jev inside.
linkedin.com/pulse/12-judges…
Hendrik Krack retweeted
5/6 Thx to organizers @AICollectiveCo, @AJs_AI, @roangws @chappyasel & My Luu, plus host @coderabbitai.
Shoutout to its intern trio behind Revolution, 1st place: a wildlife ecosystem sim running ~4,000 Jev decisions for ~$1.30.
Hendrik Krack retweeted
4/6 "We woke up a night later with 1,500 pull requests open, and not enough humans in our company to press the button."
@HKrackDev of @coderabbitai on unleashing background agents on a monorepo.
Answer: Triage ranks agent PRs by risk & review-readiness.
Nice sesh with Jev @typesafeai 🫶🏻🔥
Hendrik Krack retweeted
Kicking off the Jev Hackathon in SF 🔥
@typesafeai @allietheicon @AICollectiveCo @HKrackDev @coderabbitai @gmi_cloud
I really never should have given my parents a LinkedIn account... 😅
Such a fun conversation with @francedot - I am truly amazed by what he build with @trycua.
My personal OpenClaw uses CUA driver for EVERYTHING and it's so token-efficient, it makes Codex Desktop app look like a little token-monster sometimes tbh 👾 🙈
Your agent worked all night. Do you merge what it wrote?
Francesco Bonacci (@francedot) of Cua (@trycua) wants his agents shipping while he sleeps, without waking up to a mess he has to clean up. The hard part is staying close enough to steer them.
On this episode of The Merge we get into how he closes the loop on agent tasks, what to do with low-quality AI-generated PRs, and why a proposed patch isn't a merge.
His take: more autonomy means review matters more, not less. You still need to be able to inspect the result and push back on it.
Last night I had my premiere 🎷 with my favorite DJ and partner @lidia_schwarz at @innovitsf 🎶🫶🏻
Hendrik Krack retweeted
This week in the CodeRabbit changelog 🐰
→ Share TypeScript review configs across repos
→ Handle metrics API retries with clearer retry guidance
Define review standards once. Reuse them across your team’s repositories.
See the full changelog: docs.coderabbit.ai/changelog
Super stoked to be co-hosting a hackathon this Saturday with @typesafeai AI, the creator of the viral new model Jev, and @AICollectiveCo at our @coderabbitai HQ in SF!
Seats are limited and subject to approval. Apply at the link below ⬇️
🤖 Made with AI
This DX is truly a new milestone in how we review code in the AI era.
Think about it... the current interface has not changed since 2011... isn't that crazy?