What people miss in latest Anthropic blog is this graph - trust me those are not 30k vibe coded task managers per day.
Things to consider:
1. OAI model which solved github.com/openai/math is very computationally effective: week to train, 3h per problem.
2. It could be not LLM at all - some pure reasoning engine.
3. Recipe how to build it probably will fit in small .md file
4. 2027 will be fun
Zedmor🇺🇦 retweeted
🤖 KiroCrew
⭐ 682 stars
Imagine a dev workspace that doesn't just persist—it actually learns, self-improves, and keeps building even after your session ends.
🔗 github.com/kirodotdev/KiroCr…
#AI #MachineLearning
Zedmor🇺🇦 retweeted
Kiro Crew is here! 🚀 We open sourced this agent dev workspace tool today, used already by 39k users inside Amazon. This pace of this project is incredible: already at 500 contributors and 995 merged PRs in the last 2.5 weeks alone
github.com/kirodotdev/KiroCr…
What I love about it:
1. It starts work on its own. Cron jobs, webhooks, and messaging events kick off work with nobody at a terminal, and heartbeats watch a system until something actually needs me.
2. I can reach it from anywhere. I install one Gateway, and I can access the same agent and sessions from the desktop app, the dashboard, the CLI, Slack, Discord, or Telegram.
3. I can run it anywhere. A Mac, a container, or an EC2 instance that stays up when my laptop does not. The desktop app tunnels into whichever one I picked. Conversation history, memory, and knowledge indexes stay on that host.
4. It remembers. Tell it "always run linting before calling a change done" and that correction becomes a durable lesson, not a line of chat history that evaporates when I close the window. Failures teach it too, and after enough repetition of the same workflow it writes itself a skill. I can open the dashboard, read every lesson and skill it has accumulated, and delete the ones it got wrong.
5. It's actually safe to run at work. It enforces an OS sandbox, interactive approvals, credential redaction, and an audit log of every action.
Try it in one line, then open http://localhost:5476 and start a conversation:
curl -fsSL download.crew.kiro.dev/cli.s… | sh
Zedmor🇺🇦 retweeted
Absolutely beautiful rant about AI in Linux Kernel from Linus yesterday:
I realize that some people really dislike AI, but this is an area
where I'm willing to absolutely put my foot down as the top-level
maintainer.
Linux is not one of those anti-AI projects, and if somebody has issues
with that, they can do the open-source thing and fork it.
Or just walk away.
AI is a tool, just like other tools we use. And it's clearly a useful one.
It may not have been that "clearly" even just a year ago, but it's no
longer in question today.
There are other questions around AI (like what the economy of it will
actually look like in the end), but "is it useful" is no longer one of
those questions. Anybody who doubts that clearly hasn't actually used
it.
Yes, it can also be a somewhat painful tool, both for maintainer
workloads and just from a "it keeps finding embarrassing bugs"
standpoint.
But the solution is not to put your head in the sand and sing "La La
La, I can't hear you" at the top of your voice like some people seem
to do.
The solution is to make sure those LLM tools _help_ maintainers
instead of just causing them pain. There's no question on that side.
We're not forcing anybody to use it, but I will very loudly ignore
people who try to argue against other people from using it.
And no, AI isn't perfect. But Christ, anybody who points to the
problems at AI had better be looking in the mirror and pointing at
themselves at the same time.
Because it's not like natural intelligence is always all that great either.
The kernel project has been and will continue to be about the technology.
Sure, the social angle of working on open source is important and
often a very motivating part of the project, but in the end that's a
side benefit, not the _point_ of the project.
This is *NOT* some kind of "social warrior" project, never has been,
and never will be.
In the kernel community we do open source because it results in better
technology, not because of religious reasons.
And so we make decisions primarily based on technical merit. Not fear
of new tools.
Linus
Why what happening with @AnthropicAI is disastrous for industry: it creates direct incentive to HIDE capabilities when it's been otherwise before and work on RSI loop and make money by building softw and make money with it. It creates two realities with RSI lurking in the dark.
Zedmor🇺🇦 retweeted
Authoring code by hand HAS GONE AWAY.
Engineering module structure and architecture has not.
What is happening with new class of models in cybersecurity is like discovering that every building in the world was built to withstand magnitude 6 earthquakes, and then learning that magnitude 9 is coming. Not to one region, to everywhere, at once.
If github.com/ultraworkers/claw… implementation will survive legal precedent next logical steps are: Obsucated code -> functional copy, binary through decompiling -> functional copy, extraction from UI/behavoir of app -> functional copy. Interesting...
One huge change happened - open source projects now are not ready products or building blocks but DIY projects that you can change in hours adding any features you need. Wild.
I started this journal on Dec 20, 2025 tracking everything that is relevant trying to keep it as close as possible to truth: akimakimov.substack.com/p/ag…
Hear me out! Drop MCP it is an obscure bloat. Use CLI which are self documented and provide list of those in the context. Use daemons for background processes. Go back to basics! UNIX has great philosophy use it.
Faultpoint just got this flag: faultpoint.dev/attack-state/…
labs.hackthebox.com/achievem… #HackTheBox #HTB #CyberSecurity #EthicalHacking #InfoSec #PenTesting
Do you realize that era of merge conflict went away? “Resolve conflict between branch x I am rabasing on the mainline” - aaaand it’s gone.
Had you figured out @anthropic master plan with claude yet? They let you build for cheap on claude projects that will bring them billions on API.