Abner Andrés (@dresnite) header
Abner Andrés (@dresnite) profile picture

I ship stuff

Amsterdam
Joined March 2020
Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)Photo by Abner Andrés (@dresnite)
can we stop pretending code reviewing is of any use already?
2
204
I thought I had to build a community for my products to make money. But the last 3 months I've been very inactive. June MRR: €0 July: €39.00 August: €159.99 September: €651.00 (still 16 days left!) Turns out I just had to ship more.
3
144
ChatGPT, Grok and Claude are down. At the same time. Is AGI in the room with us right now?
1
6
567
Abner Andrés retweeted
I'm officially done reading AI-generated code. It's been two weeks since I looked at any of it. I think the IDE is officially on its way to the graveyard. The job is no longer about "writing code," so we need new tools that better reflect this new reality. While reviewing the code, I realized my only complaints were stylistic, and I wasn't finding any obvious bugs anymore. The more code I generated, the harder it became to keep track of every line. I found that my time is better spent designing ways to verify that the overall system works than looking at the code. State-of-the-art coding agents are better at writing code than I'd ever be, and I'm going to stop pretending otherwise. I still think these coding agents can't go too far without an experienced human guiding them, but we're past the point where we need to check every line of code.
1,067
803
323
9,511
1,625,198
I've been quiet for a while, but it's time for the next chapter. Recently, I've become increasingly interested in AI Engineering and AI-driven productivity, so I've started a blog where I'll be sharing my learnings, ideas, and experiments along the way. I'll share them here too. If you're interested, follow along or check out my blog (linked in my bio). See you soon!
1
161
Abner Andrés retweeted
US: *restricts US AI model because too dangerous* China: *builds better Chinese AI model* Everyone: *switches to Chinese AI model* This is why restricting models probably doesn't work, it's much more preferable (for US) to have everyone on US AI models so at least they can monitor what everyone is doing Now it's China that's monitoring what everyone is doing!
191
172
29
3,429
165,871
AI has changed the way I host my apps. Why pay a premium for cloud services when I can use an AI agent to design a secure architecture on my own dedicated server? As agents get smarter, this approach will only become easier, safer, and more accessible.
1
138
Abner Andrés retweeted
This is your wakeup call. Anthropic just took down Fable 5. It's over. Here's the thing tho: no company or government will EVER be able to take away your local models. There are Opus level models you can run right now on your home GPUs, and nobody can ever stop you from using them This is only the beginning of events like this. Day 1. More government overreach will happen. This will only keep happening more and more as models get closer to AGI Become sovereign. Buy your own compute. Before even that becomes illegal
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…
755
883
137
8,758
1,595,370
AI didn’t make coding easier. It just made more obvious who is actually a good engineer and who isn’t.
3
164
I created an app that solves a problem, but I don’t know how to market it without scaring people away. Nobody wants to listen to an ad. How can I sell you something you (probably) need without turning you off?
1
4
188
Don’t choose your LLM based on how smart it is. Choose based on output per dollar. Fable 5 is great, but I can get the same results with Composer 2.5 for 90% less money.
1
1
4
183
Fable 5 as the orchestrator, Opus/GPT overseeing and Composer 2.5 as the builder. Name a better combo.
4
110
I created a CLI tool to run safe AI loops. Enjoy!
🤖 Made with AI
1
4
137
Abner Andrés retweeted
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.
1,792
1,396
1,465
19,909
8,701,385
Abner Andrés retweeted
Ursula von der Leyen just *officially* announced at Davos: The 28th regime will be called EU–INC! WE WON.
TOTAL EU–INC VICTORYYYYYYY!!! WE MEMED THIS INTO REALITY ALL OF YOU MADE THIS POSSIBLE @euinc_petition
141
377
102
3,973
921,497
Wow!
GM! Ready to enter new REALMS? 🗺️✨ Load your #voxel or #Minecraft maps into Magic Realms, customize them with 2,500+ textures, and export directly to @TheSandboxGame, @Hytopia, and other platforms! #UGC #GameDev #WebTools #MagicRealms
1
1
15
744
Abner Andrés retweeted
Oh what! New mmo just dropped on @hytopia 👀 I’m about to try it out
Something new just arrived on @Hytopia… 👀
2
12
100
3,081
Dresnite released his new MMORPG on @HYTOPIA! We're gonna stream it together on Monday (12:00 PM EST).
3
3
51
1,205
Something new just arrived on @Hytopia… 👀
28
40
5
164
10,933
Only a few hours left until the prerelease of our @Hytopia MMORPG goes live. 🚀
7
2
67
1,547