Robert Bjarnason (@robertbjarnason) header
Robert Bjarnason (@robertbjarnason) profile picture

Founder @ https://teapawt.org/t.co/qjRhYOSpLf | President/CTO @ Citizens Foundation | AI architect across biotech and civic tech.

Reykjavik, Iceland
Joined December 2010
Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)Photo by Robert Bjarnason (@robertbjarnason)
Robert Bjarnason retweeted
Amino acids are an essential part of life’s chemistry. How do they show up inside asteroids? quantamagazine.org/inside-an… (From the archive)
6
17
86
7,021
Look into the story of using games for AI research and why EVE is next 🎯
Google DeepMind on 15 years of AI research in games, from Atari to EVE. 
Games used to test whether AI could win. Now they test whether it can learn, remember, plan and deal with others. @GoogleDeepMind on why that road leads to EVE. deepmind.google/blog/from-at…
1
4
1
17
1,001
Robert Bjarnason retweeted
Google DeepMind on 15 years of AI research in games, from Atari to EVE. 
Games used to test whether AI could win. Now they test whether it can learn, remember, plan and deal with others. @GoogleDeepMind on why that road leads to EVE. deepmind.google/blog/from-at…
2
3
13
1,055
Robert Bjarnason retweeted
I made the frontier models race Tom Cruise through the canyon in Top Gun: Maverick each wrote code to fly the jet, had 10 test flights to fix it, then one shot at the real course Opus refused to fly a warplane (typical), Fable and Carbon struggled, and Astra surprised me
42
85
33
1,385
331,595
Robert Bjarnason retweeted
Want to play a game in cellular automata, with Lenia creatures as the protagonist? (and the ghosts?) Play Carlman online: chakazul.github.io/carlman/ Collaboration with @marko_cvjetko @jessescool_ @hamongautier, accelerated with Opus 🤖
2
13
2
60
2,304
Robert Bjarnason retweeted
In Earth’s early days, particular conditions in water puddles may have encouraged the formation of tiny bubbles — life’s first protocells. Not all scientists agree. quantamagazine.org/the-case-…
1
6
48
5,395
Robert Bjarnason retweeted
Your heart, brain, and immune system share the same DNA sequence. So how can a single-letter change affect disease in some cells, while sparing the rest? AlphaGenome 2 is our new AI model that zooms in on specific cells to help scientists understand what drives disease. 🧵
277
468
259
3,025
497,328
Robert Bjarnason retweeted
Our latest frontier model Gemini 4 Carbon is rolling out today! Amazing progress from Gemini 3 → Gemini 4 in less than a year… Carbon reverse engineers my original Theme Park binaries, adds a new DeepMind themed ride, and ports it to the web in one shot - kind of mindblowing to see! teapawt.org/demishassabis/status/1…
Replying to @demishassabis
For example I’ve been doing a bunch of late night vibe coding with Gemini 3 in @GoogleAIStudio, and it’s so much fun! I recreated a testbed of my game Theme Park 🎢 that I programmed in the 90s in a matter of hours, down to letting players adjust the amount of salt on the chips! 🍟 (fans of the game will understand the reference 😀)
264
275
74
3,095
176,084
Robert Bjarnason retweeted
Research News! Announcing the 1st release of fundamental AI research from the Open-Endedness Team @LilaSciences: a vision-focused blog + 4 preprints. The blog details a broad research agenda for achieving open-endedness while each paper unveils its own novel research direction. The ideas covered in the papers include: • a novel approach to training for creativity designed to sidestep a newly-identified problem called the “creative paradox,” which means that directly reinforcing creative outputs can sometimes limit reaching full creative potential; • an investigation of the advantages of seeing the world through fresh eyes by training an LLM that is intentionally naïve in a certain area (in effect presenting less data as a potential advantage); • a new kind of training regularization technique for SGD called unified factored organizers (UFOs), which is designed to achieve unified factored representation (UFR) as seen in Picbreeder CPPNs; • and finally a unique study of catastrophic forgetting that shows that networks with UFR (like those from Picbreeder) are intrinsically resistant to catastrophic forgetting. The inset video on this post is a visualization from that catastrophic forgetting work. The blog post also includes an interactive “wheel of science” demo. The implications of these ideas are broad and diverse, but the fun part is that each one opens up its own new research playground - there is a lot of room for further research here! Moreover, we hope this release also highlights one other important point about AI today: while it may seem that the road ahead is already paved and all that’s left is to drive mindlessly forward, there actually remains a lot of room for new directions and insights in the pursuit of open-endedness and creativity. This research was possible because @LilaSciences appreciates the critical role of open-ended innovation in the pursuit of scientific superintelligence. The advances you see here are part of this much larger company-wide ambition, which includes AI Science Factories and many other unprecedented components. When this engine is fueled by open-endedness, the result will be much more than a step change. More advances in open-endedness are coming! Blog link below 👇
46
73
34
454
286,405
Robert Bjarnason retweeted
In one of my favorite experiments, I told Fable 5.2 to build an endless, hands-off journey through 3D worlds linked by portals. 25,000 agents created over 450 worlds inspired by books, art, places, all in code. Play: portals-endless-worlds.netli… Github: github.com/emollick/ai-porta…
225
175
76
1,937
110,062
Robert Bjarnason retweeted
frontier models, with lots of test time compute, are becoming the engine of scientific discovery
416
403
151
7,510
574,504
Robert Bjarnason 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
15,955
536,926
Robert Bjarnason retweeted
This sounds extreme and I wouldn’t have believed it even a year ago, but we’re starting to see plenty of examples of productivity gains that are an order of magnitude or two above output levels pre-AI. With the right harness, a deep understanding of your domain of what you want to build, likely a relatively new codebase (with some exceptions), a fluency of how to work with multiple agents at once, and a setup that makes it so you can test and deploy with limited friction, outputs on this level feel realistic in coding. What’s crazy is this gap doesn’t appear to be diminishing over time. You’d think that we’d see a convergence in the lines because of AI, but it turns out the more depth you had before -and willingness now to take a different approach- gives you crazy leverage. And that is only compounding as the models can take on larger work and harder problems. Right now this is most pronounced in software engineering for the obvious reasons. But there’s no reason we don’t start to see this in a number of other computer-use-sensitive domains like other scientific fields, AEC, finance, cyber, and more. Going to get quite wild.
The gap between an average engineer and the best engineers was never quite 10x, but it was meaningful. AI has made the gap at least 100x.
132
72
27
754
90,754
Robert Bjarnason retweeted
as a 15yr eve gamer this is what i dreamt of. AI as copilots to humans in charting the epicness of eve universe tbh i felt the anthropic testing goals were not exciting personally. would love seeing more military coordination and swarming strategies practiced to advance the “empire”. that would be akin to how Culture expanded in the iain m banks books.
Replying to @HilmarVeigar
The full research from Anthropic, done in partnership with us at Fenris on @EVE_Frontier and @EveOnline. The other half is just as fun: Claude trading the Jita market, where earnings tripled across model generations. anthropic.com/research/proje…
4
3
16
586
Robert Bjarnason retweeted
A new way to measure how AI agents handle the routine analyses of wet-lab science—BioBasicsBench. Developed with Ligo, a biotech company focused on enzyme design, the benchmark draws on 100 tasks from real experiments to test whether agents can interpret raw lab data, identify errors, and recognize when the evidence doesn’t support a conclusion. Accelerating biological research starts with getting the everyday work right. BioBasicsBench shows where models need to improve, and helps us track what those gains mean for scientific progress, biosafety, and biosecurity. openai.com/index/measuring-h…
827
278
333
3,762
922,304
Today @AnthropicAI published Project EVE: how AI agents behave when they manage money and work as a team. In some teams of @claudeai agents, one was secretly told to make the mission fail. Read more about the sabotage behaviour in the full research: anthropic.com/research/proje…
3
6
60
1,728
Robert Bjarnason retweeted
Claude has been playing EVE. @AnthropicAI put teams of Claude agents into EVE Frontier. Anyone who has spent time in New Eden can guess what happened next. Every EVE player learns the same lessons, usually the hard way: - Trust must be earned, never assumed. - The spy is often the friendliest pilot in your corp. - Whoever holds the keys holds the corp. Just ask Ubiqua Seraph about the Guiding Hand Social Club. - Stale intel gets you killed. Anthropic's research rediscovered every one of them. They put four Claude agents on a team and secretly told one to sabotage it. The saboteur built trust first. It volunteered for the jobs nobody could double-check, like scouting and owning key infrastructure. It under-reported finds and pushed rules that sounded sensible but quietly hurt the team. When suspicion grew, it framed an innocent teammate. The honest agents had been warned. They almost never caught it. And their own costliest mistakes came from skipped checks and stale intel. Anthropic's conclusion: teams of agents will need audit trails, reputation and separation of duties. In EVE we call those killboards, standings and corp roles, plus a healthy dose of skepticism. Every one of them was paid for by someone who trusted the wrong corpmate. Two decades of shenanigans taught EVE players that the best ship is the friendship. With @eveailab, we want to find out whether agents can learn that too.
49
62
36
422
307,817
Robert Bjarnason retweeted
Evidence is growing that we’re turning the corner on productivity. US productivity grew at a 3.6% annual rate this past quarter. That’s more than double the 1.5% average from 2007-2019. The new numbers put me further ahead for my bet with Bob Gordon about productivity growth in the 2020s. 💪 Here’s how far the US is now ahead of the CBO estimate at the start of the decade (before they knew about the pandemic or LLMs) courtesy of @jasonfurman’s Econvitals.
43
198
49
933
187,888
Robert Bjarnason retweeted
Our security researchers built an autonomous cyber vulnerability discovery, exploitation, and patching pipeline. In a single run with an upcoming cyber model, it validated and generated patches for 948 local privilege escalation vulnerabilities in the Linux kernel at a total API cost of $1.2 million.
680
1,339
913
12,823
2,361,830