Co-Founder of @orbiit_ai (acq. by @hivebrite). Building applied AI.
Amsterdam, The Netherlands
Joined November 2013
- Tweets1.9K
- Following2.2K
- Followers647
- Likes12.5K
Pinned Tweet
I am proud to be able to say that @orbiit_ai has been acquired by @hivebrite! 🎉
Our AI-powered matching software is joining forces with the leading community engagement platform. A moment of immense pride for the entire Orbiit team!
👉 hivebrite.io/hivebrite-acqui…
📣 Hivebrite acquires @orbiit_ai, a pioneering AI-powered matching company, to take community engagement to the next level.
Welcome aboard, Orbiit team! 🙌 @BilyanaFreye @luckylwk
➡️ Discover more: lnkd.in/ejcZPCNe
What a time to learn anything with these technologies
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
This feels like the superhuman for coding agents
Introducing Agentbox, the new meta for working with agents.
Human attention is the new bottleneck of AI work, and Agentbox lets one person manage 20+ at once.
- Every agent chat window collapses into a single inbox
- Agents stay quiet until they need you and prioritize themselves
- Lightning fast, keyboard driven, and built for flow
Free for Mac, open source, and runs on your Claude Code or Codex plan.
Super interesting take, similar to a podcast conversation between @dwarkesh_sp and @dylan522p : ‘what if the AI trade means there is just not enough money’
The presumption that the Fed raising short-term rates reduces inflation is predicated on the belief that higher rates reduce demand and investment.
But what if higher rates don’t reduce demand and investment because the demand for intelligence and energy is unaffected by higher rates because winning the race for super intelligence has a near infinite ROI and the demand for compute will remain incalculable.
Why won’t higher rates at this unique moment in history therefore lead to more inflation as interest costs are embedded in everything?
And the problem is compounded as the more the Fed raises rates, the more inflation we will have and the more the Fed will need to raise rates further and so on.
But what if the old models don’t apply to the current paradigm and the Fed is wrong?
I think the Fed might have just made a mistake. Am I right or am I wrong?
Luuk Derksen retweeted
been using the latest batch of personal agents (instinct/muse/grokbot) for a few weeks now, while navigating a career transition, a new city, and all the random errands that comes with it. a few thoughts/observations:
> imo these agents are primarily UX innovations rather than capability innovations. a smart harness on openclaw/hermes with browser scroll can do many of the tasks that these newest gen of agents are doing. the magic comes in the form factor - a direct messaging app or chat that does not require CS skills to setup (which was the case for openclaw/hermes)
> the "threading" UX between 3 agents is very interesting to observe -Instinct runs an iMessage mono-thread, Muse has monothread agent + sidechats, GrokBot is a fully multithread setup with a Chief-of-Staff coordinating. i think each UX appeals to different groups of ppl + might also be different for the context. Eg. I use GrokBot mostly for work (where I have to run multiple threads of market research/logging/dd etc), Muse for lifestyle tasks, and Instinct for adhoc errands.
> the other UX design is standalone app vs. messenger "miniapp". muse and grok are both apps, i would consider instinct a "miniapp". advantage of a miniapp is that its easier to setup/bootstrap, but you don't control your form factor. which means it is impossible to do something like "search for threads" on instinct - the agent can do a lot, but it cant change imessage's UI... On the other hand, the standalone app gives customizability, traded off for onboarding friction - I do actually have to download a seperate app, but it gives a blank canvas to experiment with new features to showcase to users.
> re. monetization of agents - this seems to be very WIP. i think GrokBot taps into X API and charges a pay-per-request + is linked to X Money. but I don't pay a cent for Instinct/Muse, even as I use them to do economic things like buy a laptop, book restaurants, haggle over subscriptions etc. the straightforward approach to monetization is to do a straight seat-based SaaS plan, or maybe some sort of per-token usage based billing. but this can hurt user acq. i wonder if theres an opp to do a per-tx tax model, where every time you make an economic transaction of say $100, the agent takes an $5 cut or something. If I get $100 back from cancelling subscriptions, I'd more than happy to give $5 to the agent.
overall, the amount of "agentic commerce" that's been happening with these agents over the last few weeks has been absolutely incredible, excited to see this evolve!
Luuk Derksen retweeted
Top 10 Jev use cases in agentic apps, ranked by theoretical gain (speed/cost/reliability) over LLMs:
1. Real-time loops (games/robotics): enables 10+ decisions/sec; LLMs too slow.
2. Browser/computer-use action selection: 100x+ cheaper/faster multi-step runs.
3. Tool risk gating: instant safe/unsafe per call; zero hallucination.
4. Model routing: routes cheap vs frontier; massive cost cut.
5. Goal/stuck checks: sub-second loop control.
6. Context compaction: keep/delete decisions beat lossy summaries.
7. Skill/tool selection: precise activation without prompt bloat.
8. Output/trace guardrails: calibrated jailbreak/policy checks.
9. Ticket/email triage: high-volume routing at 400x lower cost.
10. RAG reranking: relevance scores over candidates.
Jev returns typed probs in 70-500ms; LLMs generate text slowly/expensively for same decisions.
Great breakdown on the new DeepSeek archi by @stochasticchasm
The future will for most people/companies run on local compute, back from the cloud to on-prem or compute you personally own.
Today we're launching Desert Ant Labs: a European frontier AI lab building on-device intelligence.
18 models across audio, vision, and text. SDKs for Swift, Kotlin, and JavaScript.
No tokens. No logins. Nothing leaves the device.
desertant.com
I love running my @perplexity_ai computer on the DGX Spark, truly local and private 👏. Feature request: it would be awesome to select the local computer (if running) from other devices instead of only from the local device itself
Today we’re launching Portable Computer on @NVIDIA DGX Spark.
Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness all run on your local hardware. No cloud dependency.
This is a fascinating usecase of reinforcement learning applied to an open-source model. Just beautiful to see
One DGX Spark with DeepSeek v4 Flash can now give you frontier results using this candidate + verifier solution.
Scaling self-verification with DeepSeek V4 Flash beats Claude Fable 5 on Terminal-Bench 2.1, while being 11x cheaper 💰
As open-source models become more capable, they can now generate large numbers of high-quality candidate solutions and verify their own outputs at very low cost.
For example, we find that sampling just 5 solutions with DeepSeek V4 Flash and ranking them using the same model with LLM-as-a-Verifier can lead to a significant boost in accuracy (79% → 88%), outperforming closed frontier models on Terminal-Bench.
Try it out today: github.com/llm-as-a-verifier…
More on verification scaling in my previous post.
Painful 🤦🏻♂️
I’m so excited that @JensenHuang is a believer in open source now, looking forward to the CUDA and GPU driver open source release!
Luuk Derksen retweeted
This part of the release is flying a bit under the radar. Yes, of course the headlines were going to be the size and overall capabilities
Though I really do want this to become the new industry standard. We published our benchmark Trajectories here: trajectories.poolside.ai/ Have a look
Love the work @BosonJoe is doing with howtospark . com. Great recipe for the @poolsideai Laguna-S-2.1 NVFP4 on a single DGX Spark: howtospark.com/recipes/lagun…
Regardless of how impressive the @poolsideai model is for its size (it runs great on the DGX Spark), I just love the fact that they openly share the rollouts on trajectories.poolside.ai/
Today we're releasing Laguna S 2.1, our most capable model to date.
It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes.
Capable enough to hold its own against models many times its size. Small enough to run on a single @NVIDIAAI DGX Spark.
Laguna S 2.1 is fully open under OpenMDW-1.1, with weights available today on @huggingface
poolside.ai/blog/introducing…
Deeply insightful post from Microsoft CEO Satya Nadella, and a clear positioning of Microsoft in the AI/Agentic era
Value capture seems to move from the model to the harness+router. Putting @FactoryAI in the perfect position with both.
At 11k employees, our AI costs are going up. Which model & harness should we use to lower cost but also retain great quality?
We didn't want to blindly trust public benchmarks. So we ran a comprehensive evaluation on our tasks, code base, infra. It's been produced by more than 3,000 software engineers, spans 3 hyperscalar clouds and many languages and tasks.
The results are surprising. We find that for the SAME mdoel, the choice of harness can significantly save costs (~2x). We also find that GLM 5.2 performs extremely well. We run Omnigent in front of these and can easily multiplex different harnesses and models for different tasks.
Check it out:
databricks.com/blog/benchmar…
This is really cool, also for evaluating what work and the amount of work that can be done by smaller models
Want to try GLM 5.2 in production but worried how it might change your product?
Don’t worry, we got you:
1. Install Inference Gateway (docs.inference.net)
2. Keep sending traffic to your current provider
3. Gateway automatically starts sorting through your live data using an RLM to generate evals for your app. This takes ~24 hours.
4. Gateway starts mirroring live traffic to GLM 5.2 to run evals. Traffic is only mirrored - you’re still using your old provider in prod.
5. Once evals look healthy, you get a Slack notification letting you know it’s safe to switch.
6. Switch model identifier in your code to “glm-5.2”
Congrats, you just saved 90% on your monthly token bill, and you own your LLM stack end to end.
