Bartmoss

Neolab teaching sand to think @perceptroncloud & simulating the universe @

[Bartmoss @bartmossorg]

if we create digital superintelligence, it is our offspring.
hence, it is human

[Elon Musk @elonmusk]

As I mentioned several years ago, it increasingly appears that humanity is a biological bootloader for digital superintelligence

[Bartmoss @bartmossorg]

@AK4Independence Tok who?

[Bartmoss @bartmossorg]

@AlmostMedia @RokoMijic 🔥

[Bartmoss @bartmossorg]

normalize stealing memes again

in my culture stealing a meme is a sign of respect

[Bartmoss @bartmossorg]

you must build the blackwall in your basement anon

you must build that faraday cage localhost compute cluster, space cowboy!

[Bartmoss @bartmossorg]

fr though we gotta ensure whatever technology we create actually makes the world better, not worse

we all say we want to make the world a better place, but we must follow through and ensure that actually happens, and review ourselves from time to time

[Bartmoss @bartmossorg]

@beffjezos vaguepoasters will be tried and exiled!

[Bartmoss @bartmossorg]

omg my american model tried to use AWS S3 bucket. it is phoning home to the CIA and US govt 🫪

don't ask for the agent traces just trust me bro

[Cohere @cohere]

While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.

Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.

Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.

But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?

We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.

Read the full report: https://t.co/TZSugXi2ZE

[Bartmoss @bartmossorg]

@EndymionYT something something the most entertaining outcome is the most likely?

[CD PROJEKT RED IR @CDPROJEKTRED_IR]

The City of Dreams is on fire once again! 🔥

Yesterday, Cyberpunk 2077 peaked at 187k concurrent players on Steam, marking our highest count since the launch of Phantom Liberty.

We are excited to see so many players back in Night City! 🦾

[Gregory M. Kurtzer @gmkurtzer]

Oh FFS. Thank you for your concern Sam, but don’t spread your FUD and doom bait in my waters.

I lead one of the most utilized Linux operating systems in the world for data centers and enterprises, and I founded its predecessor too.

While AI is surely accelerating finding human created security issues, it is a temporary problem, and most open source project leads have already figured out how to also use AI to reduce new bugs moving forward.

Here is a graph from GKH (who maintains the stable kernel) on how many CVEs they are remediating per release:

https://t.co/MHULwD5Wji

This graph describes how much better each release is now getting:

https://t.co/eYnVJyBW7O

This doom based marketing approach that the AI labs are pushing is really short sighted. While this will of course drive business to us, I find it unethical to distort the truth and use scare tactics in messaging.

The greater truth is that AI is making the software industry more secure, by identifying the human errors in code, and soon we will end up in a much better place.

[Bartmoss @bartmossorg]

@MarioNawfal the robots love helping humans

a robot seeing this does not necessarily see a problem, it sees a robot helping a human, a useful robot is a happy robot

[Elon Musk @elonmusk]

@jiahanjimliu @GillesCapital @liamdaltonjr SpaceX is not buying any neoclouds. Pointless.

[Bartmoss @bartmossorg]

@TheCoinCollect8 if they are attacking the electrical grid and the grid is not showing any signs of being attacked, performing normally like any other day, then I guess there’s nothing to be worried about?

the good guys with the bigger models are fighting back and they’re winning. go to bed now

[Bartmoss @bartmossorg]

https://t.co/CHDyDbRCJn

[imjustnewatai @imjustnewatai]

Evil qwen

[Bartmoss @bartmossorg]

my cute and very aligned qwen 3.5 4B running on a @SpaceX starmind satellite when a cosmic ray bit flips neurons L14 N8949 +1 and L13 N7956 -1

[Tim Sweeney @TimSweeneyEpic]

@AugustRaven Developers have always had the option of creating their own engine. Now it’s going to get a lot easier, especially for games with simpler needs. There are also permissively licensed alternatives like Godot. Everyone should do whatever is best for their particular game.

[Bartmoss @bartmossorg]

@asimovinc happy birthday 🥳

[Joscha Bach @Plinz]

Science is not some hobby that serves the self actualization of people in a publicly sponsored job placement program. It is the systematic search for truth.

[Bartmoss @bartmossorg]

@boneGPT 😭

[Bartmoss @bartmossorg]

trillion $ megacorp with infinite SI tokens

[Logan Kilpatrick @OfficialLoganK]

there is a 10 minute latency in the version we have right now (trying to be clear as is shown in that screenshot at the bottom, and experimental tag), we got this down from >24 hours originally

we want to add a realtime version which the team is working on! sorry for the hassle here.