Rene Lengwinat (@rlengwinat) profile picture

Passionate about technology & software development at inovex.de, fitness and healthy living.

Hamburg, Deutschland
Joined August 2012
Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)Photo by Rene Lengwinat (@rlengwinat)
Rene Lengwinat retweeted
Let’s be very clear: there is value in automating tedious and repetitive and dangerous tasks; there is value in delegating certain work to our machines that can do the work tirelessly and much faster. But at the same time, let us remember that there is value in the activity of engaging one’s mind and body to discover, to understand, to create, and yes, even to struggle and overcome. Indeed, these are some of the things that make us human, that contribute to giving us meaning, that are part of the simple joy of experiencing being alive.
46
223
17
1,356
42,174
Rene Lengwinat retweeted
What everyone doing “spec-driven development” is and has always gotten wrong… aicoding.leaflet.pub/3mwlzit…
🤖 Made with AI
4
5
2
43
5,140
Rene Lengwinat retweeted
smol machines v1.15.0 has landed with support for nested virtualization with `--nested` flag It means, you can now run a vm inside a vm for your RL workloads like OSworld. Proof is in the /dev/kvm existance inside the smol vm. :) Release notes: github.com/smol-machines/smo…
6
6
1
80
3,031
Rene Lengwinat retweeted
Big announcement from @MistralAI today: ⚡ European Compute Units 🌍 Regional inference 🎯 Third-party model support starting with GLM 5.2 @MistralAI is bringing together the inference infrastructure, open models, and long-term commitments Europe needs to control its AI future, and setting a roadmap for the world. More in the blog 👇
29
54
21
429
41,750
Rene Lengwinat retweeted
Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. @rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: openworker.com (requires your own API key) Source code: github.com/andrewyng/openwor…
491
1,423
227
9,696
1,177,118
Rene Lengwinat retweeted
The goal Pelé called the most beautiful of his life was never filmed. Aug 2, 1959, vs Juventus, on Rua Javari. With @Google, we rebuilt it frame by frame. This time, the whole world can see it - goo.gle/pele . O gol que Pelé considerava o mais bonito nunca foi filmado. 2/8/1959, contra o Juventus, na Rua Javari. Em parceria com o Google, reconstruímos o lance quadro a quadro. Desta vez, o mundo inteiro pode ver em goo.gle/pele.
98
978
107
6,375
843,362
Rene Lengwinat retweeted
Don't waste your tokens!!! People are currently working on Agent Skills with instructions and scripts to bootstrap an application using an AI agent. If you are a Java developer, why do you want to do that? There are many options: Spring Boot: start.spring.io/ Quarkus: code.quarkus.io/ Vaadin: start.vaadin.com/ Plus, there are the good old Maven Archetypes: Vaadin/Spring Boot/jOOQ: github.com/martinellich/vaad… #KeepITsimple
1
6
296
Rene Lengwinat retweeted
nono.sh often ends up in comparison articles where its pitched against microVMs, within a very loose rag-tag bunch known as "Agent Sandboxes" - but the truth is, this is like comparing the fly-by-wire limits built into an aircraft control system to an end-of-runway concrete barrier - one governs every control input from within, in real time; the other stops things outside from going wrong when the plane runs out of runway. A microVM guards the host. What happens inside, is not really its concern or duty to protect . If data is exfiltrated to unknown endpoints, destructive tool calls are made, an agent malfunctions and racks up eye-watering LLM api costs, and then deletes your database - you can't really blame the VM. You got what you signed up for - strong, monolithic, isolation. Not internal governance. So nono operates at a completely different point in the security model: inside. It enforces capability-based, fine-grained policy, to intercept sensitive or destructive operations, and it audits what the agent is actually doing with tamper resistant , cryptographic claims (the blackbox recorder!). The question isn't "how contained is the damage" - it's "does the agent get to do this at all, in this particular context." They answer different questions entirely: A VM answers, "if malicious code executes, how do we contain the blast radius from breaching the host and adjacent tenants?" nono answers, "how do I give the agent some authority to use a tool to access AWS credentials and call its APIs, but not allow the same access when its curl using the POST method to send your production credentials in a payload to a public github issue. Docker not long back announced "we launched Docker Sandboxes with a bold goal: to deliver the strongest agent isolation in the market." That's Great! However, it's not really what your AI weary CISO needs to sleep better at night. Instead, it's resolving a problem that's already mostly solved - in a claimed, much stronger way. AI agents aren't highly focused on breaking isolation, something very difficult to achieve; they want to steal keys and cause wreckage from the inside. Want to see what the future malicious agent looks like? Go check out TeamPCP and their recent pursuits - they aren't bypassing hardware-level isolation with a zero-day, they're letting npm install do the job by executing a post-install scripts to exfiltrate your CI tokens. BUT - they also harmonise and are formidable when combined - which is why teams and orgs are now deploying nono directly onto AWS Fargate / Firecracker, and hardened Kubernetes bound images - one holds the perimeter; the other governs what runs inside it. You get to sleep a bit easier at night. If you interested in learning more and working with us to help shape a new approach for a new threat - we are now accepting a limited number of design partners to help us shape the future of AI Agent Security.
2
9
3
38
10,833
Rene Lengwinat retweeted
Our posts were great, but nobody seems to do an open model launch blog quite like @huggingface. This "Welcome to #Gemma4" post from @mervenoyann and crew is full of useful details ... huggingface.co/blog/gemma4
5
14
47
8,683
Rene Lengwinat retweeted
Great. Can we now all agree mcp isn’t dead - it’s now being applied where it makes sense and cli commands are also super useful :)
The next version of OpenClaw is also an MCP, you can use it instead of Anthropic's message channel MCP to connect to a much wider range of message providers. (I know, this is awkward)
1
1
2
437
Rene Lengwinat retweeted
Dirty industry secret: nobody really knows the best way to use AI for software development 📢 - 24 months ago, we copy-pasted from ChatGPT - 18 months ago, we jumped between ask mode and agent mode - 12 months ago, we told AI "you are a senior developer" - 9 months ago, we built MCPs - 6 months ago, we switched to plan mode - today, we're obsessed with skills All of this (and much more) are just early experiments and temporary hacks in a very young and quickly evolving field. So when someone says their workflow is the optimal one, they're confused at best. Stay curious, stay open, stay in control and stick to the fundamentals, and you'll come on top in this amazing tech revolution. Enjoy the ride!
67
124
16
1,386
137,765
Rene Lengwinat retweeted
In computing, we take imagination and make it manifest in the form of software and hardware. There exists a sequence of barriers through which we must pass to make it so. First, there are the laws of physics. We cannot send information faster than the speed of light. There are fundamental limits as to the amount of information we can store in a given space. Thermodynamics presents considerable engineering challenges, particularly as we craft smaller and smaller devices. Next, there is the challenge of computability. We must turn theory into algorithms, and at scale we must make those algorithms fast and efficient. Design and then architecture are the next challenge. Weaving algorithms and data into systems that are functional, understandable, maintainable, and that can evolve calls us to the exquisite dance between art and science, compelling us to push the limits of our human creativity. Organizational issues rise to consideration. One developer can do remarkable things, but to release systems that are durable, that are resilient, and that work at global elastic scale requires a team. And then there are economic realities. Our dreams may be expansive, but in the end bringing them to life may be more expensive to build and to operate that we can afford. Finally, there are moral and ethical issues. There are many things we can build out of hardware and software, but our shared humanity requires us to examine if we should build them. This is the nature of development, and why hardware and software and systems engineering remain a very human problem to which we must apply all our knowledge and talent.
18
85
12
484
37,194
Rene Lengwinat retweeted
NEW POST Powerful context engineering is becoming a huge part of the developer experience of modern LLM tools. Birgitta Böckeler explains the current state of context configuration features, using Claude Code as an example. martinfowler.com/articles/ex…
29
90
2
619
61,568
Rene Lengwinat retweeted
New blog from Embabel developer Jasper Blues on the Embabel Hub chatbot/MCP server to help learn and develop with Embabel. Dog food. Built on the JVM, with Embabel. Try it today! @java @springboot #genai #embabel medium.com/embabel/from-docs…
4
12
2,176
📝"Building a Durable Execution Engine With SQLite" Durable Execution is all the rage these days. In this post I'm exploring the fundamentals of DE, based on a minimal engine built from scratch, using #SQLite as an execution log. 👉morling.dev/blog/building-du…
10
28
6
257
62,659
The current phase in tech is likely to be more enjoyable than the earlier transitions. Once the current chaos and transition is over, there will be fewer people in the industry and rebuilding from scratch will be fun.
13
11
1
198
10,244