Basly (@BaslyAsma) header
Basly (@BaslyAsma) profile picture

Building the reliability layer for Robotics https://teapawt.net/t.co/jm3gAVbkB1 | prev @CERN

Joined October 2025
One successful run doesn’t make a reliable robot. It works in the demo. Then it fails on run 50 and nobody knows why.. We’re breaking down how Run-Fingerprint looks beyond individual runs, from every success to every failure, across an entire deployment.
23
13
2
69
2,133
Working with robots has always been harder than it should be. The intelligence was hard to access. The hardware was hard to afford. Today, both change. @makermodsai Maker Arm + Metal Arm, powered by @dreamlabs_ai 's Dream-1. Give your robot a task in plain language, right from your browser. Try it: playground.makermods.ai
41
34
12
284
27,707
2 days #PhysicalAI Expo in Amsterdam is just 4hours average event in SF
17
474
We're hosting a robotics night at @MissionRobotBay this Wednesday during @SFTechWeek Robotics, off the record - What's said in the room stays in the room. We're fed up with the robotics hype. So we're bringing together people from across the robotics industry to test real robots, give honest opinions, and talk about what actually works and what breaks. Co-hosting with @thanehunt & @Scav Only few spots left, join uss 🔽 partiful.com/e/TprLtwRJBJaBw…
10
6
2
70
5,044
Build . More . Robots
can't wait to take this bad boy for a spin
1
20
919
Basly retweeted
I'm in Austin for Deep tech week, ping me if you want to talk about Robots
1
2
1
17
1,779
The fastest unlock for any robotics system is deployment, the faster you deploy the faster you break things and learn, if you are a robotics team and am want to move from prototyping to the field sign up for our open beta !
- Are you deploying robots ? - Is it almost impossible to replicate specific scenarios and edge cases across hardware/software interactions ? Introducing oorb fingerprint, your reliability layer for deployment. compare and debug thousands of robot policy runs, in minutes .
3
2
1
36
3,489
I’m in Chicago for #IMTS_2026. If you're around, let's connect
3
16
674
This is sick
I got inspired by another post to create this web visualization and capture all the major players from every category in the foundational model economy, its very fun to play around with and see how deep some companies run. ~5T of valuations ( exluding MANGO ofc ) ~2100 companies 36 categories check it : llmeconomy.com ps : there's a lot of values and I was verifying most of them by hand but lmk if there's some outdated valuations or revenue figures that the LLM missed so I can update.
7
706
I liked the approach and wonder what’s the total of agents will be
I want to know how many agents are on the internet. Not “AI mentions” or chatbot screenshots. How many autonomous clients are actually moving out there and what they do when nobody is watching?? Well, nobody has that number! So I built a honeypot to steal it ⛓️
1
280
I’ll be at #Actuate26, let's connect if u are around!
I'm feeling incredibly excited about #Actuate26 this week, and grateful to our team who have dedicated the past few months to making sure the event is a success. It's hard to believe what this little conference has become! We're officially SOLD OUT - 1500 tickets! 3x last year. We've got 40,000 sqft of robots, 40 speakers, 2 stages, 2 happy hours, @UFBots, and 15+ community events happening during the week. See you all tomorrow!
3
1
28
1,521
She thinks “let’s get coffee” is a date. 🤓
5
6
1
113
12,412
Trying something
2
33
1,252
Basly retweeted
I was not joking, we assemble and test it today before qwen drops
-5k on my card this lovely night
1
1
15
889
Today we're launching Hebbian Robotics (YC S26) @hbr_pbc . We build APIs for evaluating data quality, without training a robotics model. Data vendors use our API to search and analyze Physical AI data at scale, getting on-demand quality signals and metrics without managing infrastructure. High-quality data is the bottleneck to the next frontier of intelligence in robotics. Buyers want data they can trust. Data providers are focused on operational excellence. They don't have the bandwidth to understand the quality of their data at scale. We're fixing this. Vendors use our APIs to understand the impact of their decisions on their data quality: - Buyers demanding per-collector hour limits? Prove compliance while we stay ahead of the workarounds. - Changed your collection SOPs? Monitor for quality drift and regression. - Suspect duplicate samples? Verify with a single API call. Before Hebbian, I trained AI models for industrial cleaning robots, and @kstonekuan spent years building large-scale infrastructure at Jane Street.
104
43
16
407
166,950
Back in the Bay, what did I miss?
2
16
770
Marble what are we having for lunch today ?
btw @heymarble_ai ordered everything for the party
1
470