Fullstack Senior Developer @ommaxdigital #ibexa #symfony #vuejs #nuxt
Munich
Joined November 2009
- Tweets4.9K
- Following62
- Followers1.1K
- Likes3K
Aleksey Razbakov retweeted
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
Aleksey Razbakov retweeted
We’ve decided to open-source a multi-agent harness we use internally at YC.
We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).
The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.
Aleksey Razbakov retweeted
This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads.
Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.
Who Am I? Will, Suffering, and Ikigai
razbakov.com/blog/2026-06-19…
by @razbakov
Water Is Memory
razbakov.com/blog/2026-06-19…
by @razbakov
Let agents help you find your purpose in life and support you in background while you living your happy life.
ikigai.razbakov.com/
#CodeWithClaude
Aleksey Razbakov retweeted
Anthropic just showed a 24-minute workshop on how to actually prompt Claude.
Taught by the people who built it.
Free. No signup. No paywall.
I've watched $300 courses that don't cover what they teach in the first 8 minutes.
Aleksey Razbakov retweeted
With the help of Claude Mythos Preview, the Firefox team fixed more security bugs in April than in the past 15 months combined.
Aleksey Razbakov retweeted
Usage limits are up, effective today we're:
1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans
2) Removing peak hours limit reduction on Claude Code for Pro and Max plans
3) Substantially raising our API rate limits for Opus models
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity.
This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
Aleksey Razbakov retweeted
Someone just built the world's first Office suite designed for AI agents.
It's called OfficeCLI and it lets agents read, edit, and create Word, Excel, and PowerPoint files from the command line.
→ Single binary with zero dependencies
→ No Microsoft Office, no WPS, no runtime needed
→ Every command supports structured JSON output
→ Path-based addressing for every element in every document
→ Resident mode keeps documents in memory for batch edits
→ Works on macOS, Linux, and Windows
→ Ships with a SKILL.md that teaches Claude Code how to use it
100% Open Source. Apache 2.0 License.
github.com/iOfficeAI/OfficeC…
Aleksey Razbakov retweeted
Paste this to your coding agent right now:
```
read the code for this repo and write a markdown doc telling me everything you can infer or know with certainty about the high level intent and idea behind this repo
ask me questions for anything that isn't clear
then pop open the doc for me to review and answer
the goal here is to make sure my intent is obvious to any agent reading this code
```
Aleksey Razbakov retweeted
Codex 5.5 hack:
"Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy"
This works like charm. It makes Codex 5.5 high perform even better than codex 5.5 extra high.
Why? Codex 5.5 is the only model i noticed that is self aware. It never makes high claims unless the model verifies everything.
This doesn't work with Opus 4.7 cuz that's a very insecure model. You can paste this prompt over and over again, the model keeps saying "you're absolutely right,....."
But with codex, after 2-3 iterations you'll notice yourself it actually patched all loopholes and this genuinely sounds like a good strategy.
Try this out, thanks me later.
Aleksey Razbakov retweeted
This is probably the most honest AI architecture breakdown on the internet right now.
9-layer AI production architecture
services/ - RAG pipeline, semantic cache, memory, query rewriter, router. Not one file. Five.
agents/ - document grader, decomposer, adaptive router. Self-correcting by design.
prompts/ - versioned, typed, registered. Never hardcoded.
security/ - input, content, output. Three guards not one.
evaluation/ - golden dataset, offline eval, online monitor. Most people skip this entire layer and ship blind.
observability/ - per-stage tracing, feedback linked to traces, cost per query.
.claude/ - agent context so your AI coding assistant knows the codebase before it touches a file.
The demo is one file. Production is this.
Aleksey Razbakov retweeted
/goal + GPT 5.5 is amazing. I can now plan really extensive refactors with e2e tests and it just works.
Aleksey Razbakov retweeted
SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY
A guy scanned an entire house with his phone. Uploaded it.
Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment.
Click → you’re inside. Every room. Every angle. Every shadow. Photoreal.
The numbers are insane:
- Agent fee on a $500k home: $15,000
- Cost to make this scan: ~$200
- Time to “tour” 50 houses: one evening
- File size: smaller than a TikTok
The science is wild too:
It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth.
AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE.
The grift opportunity is even wilder:
Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums.
One person + one phone + one weekend = a business.
Open source. Built on PlayCanvas.
Free GitHub: github.com/playcanvas
I asked my agent:
Write a blog post about why it's important to be in front of AI agents and run them in the background and live your life.
Result:
razbakov.com/blog/2026-04-29…
in 5 languages
What Level of AI Are You On? From Q&A to Ikigai
razbakov.com/blog/2026-04-11…
by @razbakov
