Alex Zerntev (@alexyz) header
Alex Zerntev (@alexyz) profile picture

AI & Software Engineer @raw_labs | Lifetime Learner 📚 | Muay Thai Practitioner 🥊 | Heavy Metal Fan 🤘

Joined March 2021
Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)Photo by Alex Zerntev (@alexyz)
Alex Zerntev retweeted
one of my favorite AI shape that got polished in 2026 is externalization of the context. like it make so much sense to not have all that info dump inside the active context. this opens up the way to more solid orchestrator/sub agent shapes that are even cooler imo.
7
6
1
68
2,912
Alex Zerntev retweeted
Building AI agents is one thing. Running them securely and reliably at enterprise scale is another. That's where OpenClaw Enterprise comes in. Here's why it matters: raw-labs.com/blog/why-opencl…
1
1
6
202
Brilliant!
first: a Photoshop approximation in ~24 hours. next: a software factory to build the apps. @echelon of @get_artcraft on Rust, coding agents and open source creative tools. "Let's Open Source the World" premieres now: youtu.be/UCL4K36SHp0
1
4
116
Alex Zerntev retweeted
We need @JensenHuang back at NVIDIA. The free world depends on it.
602
1,404
131
21,046
440,714
Alex Zerntev retweeted
pi-durable is the posix of agent programming
97
84
20
1,888
213,151
Alex Zerntev retweeted
What does it take to run autonomous AI agents securely at scale? OpenAI is already running over 500 persistent agents internally, including hundreds powered by OpenClaw. In this article, OpenAI shares the architecture and security practices behind these deployments, from sandboxing and isolated execution to agent identities, automated reviews, and observability. An important step toward making persistent agents practical, secure, and reliable in real-world environments. A great technical read for anyone building or deploying AI agents. developers.openai.com/blog/s… #OpenClaw #AIAgents #AISecurity #EnterpriseAI
3
2
5
167
Alex Zerntev retweeted
deploying persistent agents like Openclaw or Dots pose a major challenge for enterprise IT agents are more like contractors than traditional saas software, able to take proactive actions in the background without human intervention they are capable of fulfilling entire job functions but they can also take misaligned actions and write arbitrary code with unintended consequences today, we are sharing some of the best practices we use to manage fleets of claws at @OpenAI developers.openai.com/blog/s…
50
82
24
952
183,172
The fact that AI isn't delivering the expected value doesn't mean the technology is overhyped. It means we're focusing on the wrong problems.
3
39
What are you doing at AI Engineer Code? I’m:
3
69
Most AI support bots are so poorly designed that my second message is almost always: “I need to speak to a human.”
3
33
Kudos to Claude for improving its harness to plan, reason, and then implement reliably, rather than jumping straight into coding. It's gotten slower, but the quality has noticeably improved. Quality beats speed every time.
1
4
105
Nobody likes those chatbot pop-ups in the bottom-right corner of websites. They're annoying, intrusive, and rarely helpful. Why does everyone keep adding them?
4
64
Alex Zerntev retweeted
I was managing a very complex tangle of PRs and branches in chat. Thought "this needs a proper app". Spent days building a bunch of interesting alternatives. Now I have a horrible tangle of PRs and branches AND an app to maintain. Back to chat.
1
2
87
AI can create almost anything. So why does so much of it feel the same? Better models won't fix everything. Sometimes the missing ingredient is taste, attention to detail, and the willingness to iterate. A practical guide to avoiding AI slop.
1
1
10
81,826
Alex Zerntev retweeted
AI gives power to people who want to grow and know how to use new tech! Do you agree?
3
4
9
222
Yes, that is it
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
2
71
Alex Zerntev retweeted
Bullish on Andy Yen and Proton. He gets it. The culture war, or rather the loss of identity some engineers feel as AI redefines our jobs is difficult; I sympathize. Also understand that he runs a business and might has limited patience when we now had two years to process, learn, change and grow.
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
118
98
27
1,700
225,167
Alex Zerntev retweeted
Most people don't have a motivation problem. Tthey have a sleep problem.
256
232
37
6,383
243,203