Hendrik Krack

388 posts

Hendrik Krack banner
Hendrik Krack

Hendrik Krack

@HKrackDev

Building the future of code review @CodeRabbitAI Host of The Merge, Founder https://t.co/PrQJ9avJtj Sharing what I learn from founders, engineers, and open-source builders

San Francisco, CA Katılım Ocak 2025
378 Takip Edilen313 Takipçiler
Sabitlenmiş Tweet
Hendrik Krack
Hendrik Krack@HKrackDev·
Most founders dream of VCs knocking on their door. @tannerlinsley has had that for years. And he keeps saying no! In my conversation with him, he shares the struggle of keeping @tan_stack, an OSS product used by millions of developers, free of monetary influence.
English
18
12
254
30.4K
Hendrik Krack
Hendrik Krack@HKrackDev·
Coding agents now handle the manual coding. This means software engineering is shifting upstream - from writing code to orchestrating systems, defining intent, and making product decisions. On the latest episode of The Merge, @ElectricSQL co-founder @thruflo explains why we’re all becoming product managers now… and why managing state for multi-agent systems is the next big infrastructure challenge. We also cover: • Why declarative sync is replacing traditional fetch patterns • How to build reliable multi-agent workflows • The surprising rise of Elixir for agent systems Full episode here ↓
English
4
8
24
3.5K
Hendrik Krack
Hendrik Krack@HKrackDev·
Sonnet 5 just dropped! > Our benchmarks show the new model improves bug-catching precision on complex tasks, though overall recall dropped slightly. > It behaves like a mid-level engineer, autonomously writing tests and self-correcting its own code during long-horizon tasks. > It's highly verbose nature results in elevated reasoning token counts and higher operational costs at scale - so be mindful of that! Checkout the full @coderabbitai review with my colleague @JuanPa below 👇
English
2
4
12
2.4K
Hendrik Krack retweetledi
CodeRabbit
CodeRabbit@coderabbitai·
CodeRabbit Agent now runs in Discord. PR fixes, automations and code work, in the channels your community already uses. Scoped so your server can't be misused. Free for open source.
English
3
7
22
3.8K
Hendrik Krack
Hendrik Krack@HKrackDev·
@parker__conrad Nice, realtime voice gets much easier to ship when it fits the same AI SDK path teams already use.
English
0
0
1
81
Hendrik Krack
Hendrik Krack@HKrackDev·
@awesomekling The best programmers I know get weirdly excited when the clever solution disappears into something users never have to think about.
English
0
0
2
195
Andreas Kling
Andreas Kling@awesomekling·
A lot of programmers are basically fans of programming itself. It’s all about them. They have mastered Rust or Haskell or Zig or whatever, but their objects of veneration are useful mainly as a backdrop to their own cleverness. Anyone who will spend six weeks rewriting a working system in a new language to make the types nicer is more into the rewrite than the product. Extreme technical obsession may serve as a security blanket. If you are the person who knows every flaw in the architecture, every impure abstraction, every place where the old code fails to express its true intent, you already know what to say in every meeting, which is so much safer than asking whether users care. Your obsession with refactoring is your beard. If you know absolutely all the trivia about borrow checkers, effect systems, async runtimes, and build tools, it saves you from having to know anything about customers, deadlines, support, sales, documentation, or whether the thing actually helps anyone. That’s why it’s excruciatingly boring to talk to such people: they’re always asking you questions they know the answer to, and never shipping anything that answers a question users actually asked.
Anime Outsiders@animeoutsiders

I don't care what he thinks about video games, Roger Ebert had the ultimate redpill on nerd culture as a whole. This basically describes every fandom on earth, and once you see it, you can never un-see it.

English
86
180
2.3K
195.2K
Michael Grinich
Michael Grinich@grinich·
Being a founder means your "unit of work" is typically a meeting. I talk with customers, candidates, execs, eng teams, investors, etc. So to make myself feel better I made a GitHub-style activity chart. Green! ✅🤣
Michael Grinich tweet media
English
39
8
464
66.5K
Juan Pa
Juan Pa@JuanPa·
Wow wow wow What? Fable is back!?
Juan Pa tweet media
English
3
1
14
2.1K
Konrad
Konrad@yoimkonrad·
@HKrackDev are you bringing AC units with yourself?
English
1
0
2
83
Hendrik Krack
Hendrik Krack@HKrackDev·
Euromaxxing starter pack… 🛫
Hendrik Krack tweet mediaHendrik Krack tweet mediaHendrik Krack tweet media
English
2
0
6
328
Hendrik Krack
Hendrik Krack@HKrackDev·
@antirez Agreed, the open corpus and OSS work were global from day one, so pretending the benefits can be neatly fenced off feels detached from how this was built.
English
0
1
1
508
antirez
antirez@antirez·
Modern AI resulted from research made also by many non-US scientists (Hinton, the French folks, Linnainmaa, many others). The pre-training corpus was produced worldwide with massive code contribution from Europe OSS. What is happening with frontier LLMs is unacceptable.
English
56
161
1.2K
58K
Hendrik Krack
Hendrik Krack@HKrackDev·
@alex_j_meyers @garrytan Company memory gets way more useful when it sits inside the coding flow instead of becoming another place engineers have to remember to check.
English
1
0
1
64
Alex J Meyers
Alex J Meyers@alex_j_meyers·
Garry, been following you for a bit. I work at Gusto and loved your talk you did with Eddie. I’ve been using GBrain on my personal OpenClaw for a bit and recently have been adapting it for Gusto’s Claude Code flows (I had built an adapter but just ripped it out for your Claude Code MCP). Getting GBrain hooked into Gusto’s MCP stack and workflows has veen been a bit of work, but oh my lord it was so worth it. Claude Code with MCPs to our data sources - nice, but still kind of an idiot. Claude Code with GBrain indexing my Slacks, meeting notes, documents & dashboards - PRICELESS!! Now I’m building loops to automate my PM grunt work and focus more time talking to customers. Wouldn’t be doable without your inspiration & GBrain. Thank you 🙏
English
1
1
11
6.5K
Garry Tan
Garry Tan@garrytan·
I think one underestimated thing when we look back on it was how useful it is to have your own personal brain and company brain in 2026 at the dawn of usable AGI AGI gives you the intelligence You still have to collect your personal context to get the real unlock
English
159
77
1.2K
84.6K
Hendrik Krack
Hendrik Krack@HKrackDev·
@lilianweng Scaling laws are one of those rare tools that turn model building from expensive guesswork into an engineering problem.
English
0
0
0
215
Lilian Weng
Lilian Weng@lilianweng·
A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way to help us reason about the optimal compute allocation between data and model size before committing to a large run. The post covers what scaling laws predict, how compute-optimal allocation works, why Kaplan et al. and Chinchilla disagree, and how data limits + fitting details make extrapolation tricky. lilianweng.github.io/posts/2026-06-…
English
66
585
4.7K
436.8K
Hendrik Krack
Hendrik Krack@HKrackDev·
@AravSrinivas is it really temporary though? I feel like as soon I mastered one exciting but also painful challenge, SF throws a new torturing workload at me, disguised as an amazing growth opportunity... 🥲
English
0
0
1
105
Aravind Srinivas
Aravind Srinivas@AravSrinivas·
The best way to build a high pain tolerance is to remind yourself that the pain is temporary
English
117
256
2.9K
116.2K
Hendrik Krack
Hendrik Krack@HKrackDev·
@perrymetzger A strong open-source ecosystem is probably the best counterweight here because it turns this from an ideology fight back into a builder race.
English
0
0
0
236
Perry E. Metzger
Perry E. Metzger@perrymetzger·
I've said for years now that most AI Doom ideas are fantasy, but that the very real result of ham-fisted anti-AI lobbying and PR by the EA cult might be the destruction of the West and Western values at the hands of countries like China. Let's hope I'm wrong.
English
33
32
420
136.4K
Hendrik Krack
Hendrik Krack@HKrackDev·
Spicy chat w/ @GeoffreyHuntley with some good opinions that will make you think about our future as an industry...
geoff@GeoffreyHuntley

Some personal hot takes from AI: engineer Miami follows... 1. Software development is a dead-end profession because anyone can be a software developer now. 2. Anyone can use Cursor or any other tool and generate code. Being a coder and being a software engineer are different. 3. Computers used to be gated; now everyone has the power to make computers malleable. Everyone is a software developer now, but that does not mean they are software engineers 4. If you cannot demonstrate how a coding agent works, you are just a consumer and have imposed an artificial glass ceiling on your career as a software engineer. 5. If you are curious, you will have a job. If you have not been curious in the last two years, you are replaceable. 6. SaaS per-seat economics may become unstable as customers need fewer people to achieve results, prompting founders to think about new unit economics 7. Most companies will take two or three years (or more!) to figure out AI transformation. 8. Some companies are already building AI native teams of five to ten people who can build with the grain of AI 9. There will be an explosion in the number of software developers. Software development is now essentially free, and tokens are cheaper than humans 10. Not enough engineers know what it means to be a product engineer 11. JIRA ticket monkeys are cooked 12. If your company has banned AI, you should quit that company 13. AI is more like a musical instrument than just a tool play with it, make discoveries, build intuition learn where AI is good and where it fails

English
0
0
3
174
Hendrik Krack
Hendrik Krack@HKrackDev·
Not sure if I agree - I think people are generally scared bc they can't keep up - even devs and tech leaders out side AI ecosystem are starting to feel anxiety, many ppl are terrified. I believe in a great future but to be fair, even in Silicon Valley we don't know for sure the outcome of all this will be beneficial if we don't align it well
English
1
0
3
1.3K