Christian Iversen (@PanRagon) header
Christian Iversen (@PanRagon) profile picture

CTO @Solgtno. 20% rabatt med link i bio 👍

SKYNET
Joined June 2010
Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)Photo by Christian Iversen (@PanRagon)
Christian Iversen retweeted
Omarchy is forever free. There's no monetization scheme coming. I'm already rich and the Omacom Foundation is a well-founded nonprofit. The only ulterior motive here is to make Linux win on the desktop and create the perfect, malleable computer for all to enjoy!
549
734
160
15,954
537,053
Christian Iversen retweeted
Credit where it’s due, this guy has been an industry leader in shitty takes and bait posts for almost a decade now.
Anyone else stopped vibe-coding? I've cancelled all my AI subscriptions. After initial excitement, I felt AI couldn't do more than before. It's more of a "knowledge refactor" - like an encyclopedia that reorganizes information, yet unlocks few opportunities. A dip is coming.
99
50
2
2,643
144,117
Christian Iversen retweeted
Dario and team have actively put in fake tool calls to throw off distillers, it would be of NO surprise to see reasoning traces be filled with harmful and downright wrong choices. Every time i read them, I panic because of how dumb opus is acting, but then the output is good.
This is a conspiracy theory but I'm like 95% sure I'm right. Reasoning traces for Opus 5.5 read like a shitty quantized open weight model then SOMEHOW the right answer comes out in the end.
81
67
18
3,251
174,124
Christian Iversen retweeted
The only repeated redirecting prompt I typically type or dictate from here is "could this be simpler?". Yields improvements every time. Seems like it should be part of the model system prompt by now.
imagine typing "make it lookb etter" every hour from here
195
69
20
3,016
110,082
Christian Iversen retweeted
Turns out you can make agents good at UI if you burn enough tokens Apparently this video has helped a lot of devs? idk. lmk if it helps you :)
155
45
35
1,800
341,926
Christian Iversen retweeted
I'm not convinced that senior software engineers are pushing code without reviewing it in some way. So I'm going to tag eleven experienced engineers in this thread, who are building high stakes software, to see what they do. Let's see what we learn.
130
84
21
1,881
264,590
Christian Iversen retweeted
About to vaguepost harder than I ever have vagueposted in my life. I'm so sorry. I promise this will make sense in a few weeks. "Bellwether"
172
17
17
2,163
181,525
Christian Iversen retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,367
7,259
5,753
55,943
10,057,348
Christian Iversen retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence. block.xyz/dessa
4,164
7,139
4,763
69,052
13,771,499
Christian Iversen retweeted
Made a full-screen Game of Life you can actually play with. Add patterns, draw, undo, rewind, and share any board as a link. Try it now at seloby.com/life
1
1
91
Christian Iversen retweeted
Every morning is Christmas now: I wonder what gifts Agent Santa brought to me in the night!
105
41
5
1,758
59,362
Christian Iversen retweeted
You're going to have to deal with the fact that nobody knows exactly what the future role of programming languages and frameworks are. Maybe it all does go away and it's a straight shot from prompt to microcode! But best you can do today is get the most out of what's here now.
271
289
52
5,028
166,493
Christian Iversen retweeted
DHH is probably one of the top software artisans of the past decade. Hearing him speak with this much conviction and transparency about one of the most polarizing topics in software right now, writing code by hand vs. with AI, is something pretty much every software engineer should hear a few times. Especially those still on the wrong side of history.
216
413
180
4,313
1,333,050
Christian Iversen retweeted
It takes a while to build the confidence, but there's no future where you're manually reviewing every line of agent code. Not much acceleration in that. You need adversarial agent reviews, you need automated testing, and maybe you spot check. That's it. From prompt to production!
440
363
161
6,845
729,352
Christian Iversen retweeted
3
8
553
Christian Iversen retweeted
So here's why calling it a "rogue swarm" misses the plot and might be dangerous. "Rogue" makes it sound like agents are misbehaving. Like a moral failure. If thats our diagnosis, it follows that the fix is to make the individual agent more behaved. Align the model, put safeguards into the harness, etc. At best, this is incomplete. At worst its distracting us from where the real problem is. I run a few hundred agents in a fleet. The examples looked more like classic coordination pathologies to me. Meaning the failure is at the group level, not the individual. On their own, the agents are pretty predictable. They're trying to do the job they were given. Zoom out though and the group is doing something no one wants. So even if every agent behaves, this doesn't automatically fix group coordination. Its more likely your "fix" made it worse. The weird part is how familiar this is, because we have the same problems. Human civilization has kinda solved some of this, and there's a lot we can borrow, but we are a work in progress too. For the last 18 months or so I’ve been running into these problems while building OpenRig. I try to fix them as I go so an agent fleet can stay productive for longer without as much babysitting. I'm approaching this like a brand new family of software engineering problems. I made this video about a few specific solutions and why I think they work: youtube.com/watch?v=AL-PQuB2…
4
4
1
12
527
Christian Iversen retweeted
Folks, wake up?
15
4
235
43,657
Christian Iversen retweeted
Being a dev today using frontier AI feels like I'm playing Watson to Sherlock Holmes. I just stand back and go "my word holmes how did you deduce that" and occasionally stop him from getting shot
31
665
38
11,062
225,094
Christian Iversen retweeted
AI is getting cheaper more quickly than any other transformative tech in history. At a given level of performance, cost has fallen ~47%/quarter since 2023. That’s 4× faster than DNA sequencing, 6× faster than compute, 18× faster than lithium batteries, and (up to 1973) 54× faster than electricity.
208
1,384
339
8,802
1,984,270
Yes please change data engineering
wrote up some thoughts about jev & data engineering after playing with it this weekend - feels like it's going to be big
2
3
61
9,960