Staff Research Scientist at @instadeepai
Kigali, Rwanda
Joined March 2013
- Tweets159
- Following13
- Followers323
- Likes120
Arnu Pretorius retweeted
GPT-6 Astra routed this PCB in 33 minutes. @DeepPCB took 2.
Same board, same component placement.
The board is STRF, an open-source RF-to-USB dongle: 4 layers, 39 components, 98 connections.
But the interesting difference isn’t just the time. Look at the USB data pair in the image. Astra (left) routed it across both outer layers, using four vias. DeepPCB (right) kept both traces on the top layer with none. Across the whole board: 14 layer changes with Astra, 6 with DeepPCB.
These are routing decisions. Every trace you commit changes the space available for the next one. Where to stay on a layer, where to change layers, and which detours to avoid are exactly the decisions a specialist routing engine is built to make.
Our natural-language assistant, Cooper, reviewed the board and recommended settings for the router. It didn’t route the board. DeepPCB did.
That is our architecture: an LLM (Cooper) translates designer intent into constraints and orchestrates the tools. A specialist engine does the routing.
This illustrates why Astra shipping is an opportunity for DeepPCB.
The opportunity isn’t LLMs versus specialized routing engines. It’s LLMs using them.
Arnu Pretorius retweeted
@OpenAI GPT-6 Astra one-shotted a real board last week: schematic, placement, routed four layers. It worked.
We re-routed it. The board has 5 track widths and 1 net class, declared empty, so 4 of those widths have nothing to check them against.
And 9 of its 32 vias sit inside pads, on a 27 net, 4 layer board that never needed one.
Our routing: zero in pads, every width under a rule, in 15 minutes.
Not reasoning failures. They come from the router underneath. Better models mean more boards, and all of them still need routing.
Astra, or any model this good, can already drive the DeepPCB router through our API. Or you can just use Cooper!
Check out our routing: app.deeppcb.ai/shared/OkkY9e…
Arnu Pretorius retweeted
🤖 Cooper is live: your layout expert, on demand.
It checks your board before @DeepPCB routes it.
Upload a board. Cooper tells you what’s wrong before you route, fixes it once you confirm, then drives the engine.
96% mean completion, DRC-clean.
It flags it. It fixes it. Done.
Try it now: bit.ly/4vnMzfN
#ElectronicsEngineering #PCBDesign #PCBLayout #AIAgent #DeepPCB #Hardware
Arnu Pretorius retweeted
🎙️ The latest episode of Let’s Talk Research is now live!
Kicking off 2026 by reflecting on our year of research and what's next for the team with InstaDeep’s Head of Research and Development, @AlexLaterre. 🧵⬇️
Arnu Pretorius retweeted
We're extremely proud to share Daniel's achievement as part of our first oral presentation at @NeurIPSConf, representing an opportunity for AI researchers in Madagascar and across Africa to push new boundaries on the world stage. 🗺️
From Africa to the world!
We’re so proud of Daniel Rajaonarivelomanantsoa, a PhD student from Madagascar and a scholar at the Google-funded AI for Science program at @AIMS_Next.
His paper, co-authored alongside his peers at @instadeepai, was selected for an oral presentation at NeurIPS, placing it among the top 0.3% of over 21,000 submissions worldwide and making him the first Africa-based researcher to achieve this milestone! 📷
Daniel and his team identified ways to make AI perform up to 126% better. Read all about it in this @ITNewsAfrica article: itnewsafrica.com/2025/12/mad…
Arnu Pretorius retweeted
From Africa to the world!
We’re so proud of Daniel Rajaonarivelomanantsoa, a PhD student from Madagascar and a scholar at the Google-funded AI for Science program at @AIMS_Next.
His paper, co-authored alongside his peers at @instadeepai, was selected for an oral presentation at NeurIPS, placing it among the top 0.3% of over 21,000 submissions worldwide and making him the first Africa-based researcher to achieve this milestone! 📷
Daniel and his team identified ways to make AI perform up to 126% better. Read all about it in this @ITNewsAfrica article: itnewsafrica.com/2025/12/mad…
Arnu Pretorius retweeted
🧩 Proud to share that our research introducing MEMENTO, a memory-enhanced framework for neural combinatorial optimisation, has been selected as a Spotlight paper at @NeurIPSConf 2025! 🎉
👇 Hear from lead author, @ChalumeauFelix in the video below.
Arnu Pretorius retweeted
In the lead-up to @NeurIPSConf 2025, we’re answering your top questions about our research.
Hear from Daniel Rajaonarivonivelomanantsoa as he explains how inference-time search enables stronger performance over zero-shot approaches 👇
Arnu Pretorius retweeted
🚀 Proud to share that our research showing how inference-time strategies can break the reinforcement learning performance ceiling has been selected for an oral presentation at @NeurIPSConf 2025! 🎉
👇 Hear from lead authors @ChalumeauFelix and @ruanjohn in the ▶️ below.
🧵⬇️
Arnu Pretorius retweeted
Thrilled to announce that Oryx, our best-in-class algorithm for offline multi-agent reinforcement learning (MARL), has been accepted at @NeurIPSConf 2025! 🎉
Hear directly from lead author @MahjoubOmayma👇
Arnu Pretorius retweeted
We are heading to @NeurIPSConf 2025! 🎉
Our Africa-based Reinforcement Learning team are making headlines with:
3️⃣ Accepted papers
✨ 1 Spotlight (top 3%)
🎤 And our first-ever Oral presentation at NeurIPS (top 0.3%)!
🧵⬇️
Arnu Pretorius retweeted
At this year’s AI Day, we came together with our colleagues from @BioNTech_Group to showcase how we are advancing the frontier of Bio AI, with a look ahead at what the future has to hold in our rapidly accelerating field 🌠
Learn the highlights below: 🧵⬇️
Arnu Pretorius retweeted
The poster session at #DLI2025 reflects the Indaba’s mission: building AI in Africa, Urunana (hand in hand).
Researchers from early-career to experienced experts shared work spanning healthcare, African language processing, and environmental and agricultural applications, all with a strong focus on African contexts.
It was an invaluable space for feedback, mentorship, and collaboration, helping presenters refine their methodologies and strengthen the impact of their research.
Explore the posters here: deeplearningindaba.com/2025/…
#DLI2025 #Indaba2025 #Urunana
Arnu Pretorius retweeted
🚀 We’re excited to unveil the first lineup of technical tutorials and practicals at #DLI2025!
These sessions go beyond training—they reflect our mission of building AI in Africa, “Urunana” (hand in hand). Attendees will gain hands-on experience, exploring advanced topics:
Pracicals:
✨ Machine Learning Foundations
✨ Generative Models & LLMs for African languages
Tutorials:
✨ Mathematics of Deep Learning
✨ Introduction to Deep Generative Models
📌 All tutorial content will also be available online after the Indaba. Don’t miss out—subscribe here 👉 lnkd.in/eCgXRqsV
Arnu Pretorius retweeted
ChatNT has been featured on the front cover of @NatMachIntell!
This exciting opportunity allows us to share our proof-of-concept for a generalist genomics AI with a wider community of scientists and researchers around the world. 🎊
Arnu Pretorius retweeted
📆 Six months, four publications, one cover.
We’re halfway through the year and InstaDeep research is powering ahead with multiple boundary-pushing papers published in the @NaturePortfolio!
Catch up on the highlights below 🔽
Arnu Pretorius retweeted
We’ve talked routing—now let’s dive into placement! Discover how DeepPCB Placement elevates your PCB design process 🚀
Real-world use-cases showing why placement + routing = winning combo🏅
👉 bit.ly/4jxGwyL
ALT Routing after bad placement
ALT Routing after DeepPCB placement
Arnu Pretorius retweeted
👩💻Hear from the women making history in AI today.
On #WomensHistoryMonth, join women from the InstaDeep team around the world as they share how they're building, coding, researching and connecting to create a better, fairer world through AI innovation.