Roy Derks πŸš€ (@gethackteam) header
Roy Derks πŸš€ (@gethackteam) profile picture

AI DevRel & Developer Experience at IBM ⚑ πŸ₯‘ Tech Author, Speaker, Entrepreneur πŸš€ Sharing opinions (βœ‰οΈ hello@hackteam.io)

Santa Clara, CA
Joined November 2016
Roy Derks πŸš€ retweeted
i wrote a deep dive on software factories in practice and how i operate mine. if ur uncertain at all about this term, this post is for u πŸ‘‰ tej.as/blog/source-sink-drai…
6
5
99
5,562
Roy Derks πŸš€ retweeted
sharing source code for random projects in github is over starting from scratch is often more efficient than having your coding agent start from a codebase generated by a completely different model and harness
5
1
10
521
Roy Derks πŸš€ retweeted
if you’re afraid AI will take your job, then it probably will
1
2
8
447
Roy Derks πŸš€ retweeted
so many gems and great tips in this talk from @yminsky about how to improve your codebase for agents β€’ agents thrive on feedback, and types are one of the best kinds β€’ make illegal states unrepresentable with types, and it enforces global rules across your codebase β€’ property based tests, fuzzing, and even full-system deterministic simulation testing β€’ expect tests: just print stuff out and capture it in the test. makes behavior legible. it's very similar to how compilers have fixture tests, it reduces the review surface area β€’ formal methods used to be very expensive: seL4 is about 8,700 lines of C and took around 25 person-years, with 23 lines of proof for every line of C code, but agents change the roi youtube.com/watch?v=rUYP4C29…
130
181
35
2,691
369,680
Roy Derks πŸš€ retweeted
Replying to @gethackteam
@contextmode If someone engages with this post and signs up, give them unlimited credits for this week and make sure they can use Claude seamlessly without any issues.
1
1
2
128
Roy Derks πŸš€ retweeted
AGNTCon + MCPCon with @nickytonline and @gethackteam πŸ‘πŸ½ thanks for coming to my talk!
5
4
55
1,161
Roy Derks πŸš€ retweeted
I'd much rather work with someone who flexes much they accomplished with the fewest amount of tokens vs how many tokens they spent, and I sense this is a major trend in general How we quantify this as an industry is still TBD, probably a major new set of benchmarks
82
27
15
545
643,186
Roy Derks πŸš€ retweeted
We automated writing code and immediately started writing 800-line instructions about how to write code Software developers remain undefeated
2
2
10
648
Roy Derks πŸš€ retweeted
Saying software is dead because anyone can build it is like saying photography is dead now that everyone in the world has a camera in their pocket Not only is it not dead it's the beginning of the Kodak Brownie moment for software, and we will see an absolute explosion of it It will be the first generation for who building software will feel no different than using it. This is crazy! The quality and bar of what we expect from our everyday apps will be raised dramatically, we'll have personal software, we'll have disposable software, and agents will be the foundation for most of it Tech has always been chaotic and evolving, the people who have been able to adapt and move in front of new opportunities have always excelled, this is nothing new, I'm seeing it now and we'll see it 10 years from now Find the opportunities in the chaose and disruption, there are countless of them
235
367
101
3,314
311,029
Roy Derks πŸš€ retweeted
If you want PMs and designers to build with agents, give them a starter app with your auth, design system, tests and preview deployment already wired up. Telling people and their agents to follow engineering standards works better when they can start from a working example.
1
3
6
541
Roy Derks πŸš€ retweeted
Only in SF😭😭😭
48
237
33
4,637
128,021
Roy Derks πŸš€ retweeted
Going to bed these days
151
495
70
9,291
292,805
Roy Derks πŸš€ retweeted
Hard choices, easy life. Easy choices, hard life.
203
663
81
7,639
304,245
Roy Derks πŸš€ retweeted
Little summary
855
256
205
6,942
1,000,922
Roy Derks πŸš€ retweeted
Sonnet 5.5 is out. It gets remarkably close to Opus 5.5 on most coding and agentic work, at a fraction of the cost and noticeably faster. Opus is still the go-to for the gnarliest, long-horizon problems. For everything else, Sonnet 5.5 is going to be hard to beat.
19
6
1
137
5,401
Roy Derks πŸš€ retweeted
Stop caring so much about model releases. Focus on the harness, and improving the environment your agent operates in. You'll find yourself far ahead of the curve.
141
146
40
3,944
169,797
Roy Derks πŸš€ retweeted
jev is fun to play with but you have to be careful shipping it to prod, over the past few days we accidentally racked up $3.55 in usage
103
138
15
7,658
245,101
Roy Derks πŸš€ retweeted
Replying to @anshnanda
we built muse from scratch, but it is definitely heavily inspired as a product by openclaw. After I used openclaw in january I bought hundreds of mac minis for the MSL team and lots of us fell in love with using openclaw (and other personal agents). @steipete is a genius and his harness was pioneering from the jump. I think a lot of people were inspired by it. our goal with muse was to build something like openclaw that we could make safe and secure and easy to use and scale to billions of people.
109
248
111
5,129
1,234,442
Roy Derks πŸš€ retweeted
When a multi-agent demo finds more bugs, check whether it also searched more code and spent more tokens. Compare the same scope and budget before crediting the architecture. A bigger search can produce a bigger result without being more efficient.
1
3
493