generalist dev and football lover - building @attive_ai and Cursor Ambassador in Denmark
Joined September 2017
- Tweets 744
- Following 326
- Followers 213
- Likes 1,092
92 Photos and videos
Fernando Abolafio retweeted
21h
one last hurrah for our @cursor_ai ambassadors that were in town for compile.
from singapore to serbia to mexico to australia and beyond, more than 40 of our ambassadors flew across the globe to be in sf for our inaugural event and we are so beyond grateful 💛💛💛
20
17
205
8,018
Inspiring
2
79
Fernando Abolafio retweeted
Jun 16
Please welcome our new Cursor Ambassadors who joined this week
@benibauer3
@techking_007
@Cbiux_04
@vishalnai56
@ManuAF6
@AleRepetto5
@felix_schiessl
@SergeiChyrkov
@dmenchaca15
@shabskalambaie
More to come!
38
10
175
5,303
Jun 15
Por favor 🤌
25
Jun 15
Doing something wild today: coding by hand
Gotta keep those muscles from atrophy
19
Fernando Abolafio retweeted
Jun 9
Claude Fable 5 is now available in Cursor.
It sets a new state of the art on CursorBench at 72.9%, 8 points above the previous best.
265
454
6,126
1,197,894
Jun 8
how to create a solid loop with @cursor_ai:
1. create a weekly automation to inspect Sentry and other logs and create issues in Linear for it
🧵
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
1
215
Jun 8
3. Create a third automation that for small changes (based on priority) will review and maybe even merge the PR
2
39
Jun 8
You can play with the priorities to handle it differently such as tagging people in Slack for high sev.
But that’s it - you got yourself a loop
11
Jun 8
this video is such a gem in introducing effect. I've related a lot to what make it stand out to me which is dependency injection done the right way and composability.
youtube.com/watch?v=85yz418T…
24
Jun 5
Met a Scottish at a bar today. He was telling me how he thinks Scotland stands a chance against Brazil (they are in the same group in the World Cup)
The worse part is that I don’t think he is wrong 🤌
77
Fernando Abolafio retweeted
I use a metaphor of a problem tree. Go up the problem tree and take a different approach for the solution and the resulting problems are smaller/easier to deal with. Gotta prune those primitives.
1
2
62
3,440
Jun 4
Many or most problems of scale are not code, they are people.
Also there’s the concept of “aptitude” yes- code became more accessible that more people will want to do that.
Youtube gave everyone the possibility to broadcast, but not everyone wants to do that. The common sense might have said otherwise, by looking ahead of its time.
Jun 3
"Engineering, product, and design are all merging into a 'builder' role"
Yeah... I'm not so sure. This feels like an oversimplification and podcast talking point. Reality is a lot more complex.
Even with 1000 "Member of Technical Staff" titles, someone still has to wake up and care 100x more about Product or Design than anyone else. It is their Main Thing™
That's not to say MTS titles are universally bad, but I think they're an example of this 'builder' talking point that's become bastardized.
AI and coding agents have made generating code easy and yet... you're in for a world of pain if non-engineers ship a bunch of slop and don't have great engineers to tame the complexity.
The SF hivemind has a tendency to overfit what works at startups for every company. And to be fair, sometimes this is true! Startups can be a leading indicator for how the industry is changing and often cause disruption.
However, it is going to be incredibly hard to disrupt the extremely human parts of corporate jobs. You really think there's going to be a PM who also does some engineering and design on the side at JPMorgan Chase?
This is true for the simple parts of most jobs, like people wanting to have ownership over something and do good work, move up a career ladder, support their family, get paid well, make an honest living...
And also the hard parts: internal politics, some critical business system that has a bus factor of 1 which has been running for 15 years and isn't documented anywhere because it's that guy's job security. The real world has a lot of this stuff.
It's easy to pontificate about all roles collapsing but it's actually really nice to have a specific person or team who is an expert in one thing that you can work with. I don't expect that to change. Further, I think AI disruption to knowledge work will take decades to play out because it is more fundamental to the human condition (e.g. sociological/organizational) than pure intelligence.
1
41
May 30
Yep
24
Fernando Abolafio retweeted
May 28
Power users account for a large share of AI activity, and the gap is widening.
6
12
133
29,388
May 26
Whats a non obvious model you like?
Been trying the DeepSeek, Qwen and others but haven’t found a good daily assistant that has yet a well rounded experience such as GPT/Claude.
1
1
47
May 26
DeepSeek v4 pro is pretty capable and has a decent personality but the reasoning is very lengthy and annoying
23