building...
Joined October 2019
- Tweets 288
- Following 1,402
- Followers 345
- Likes 5,723
40 Photos and videos
Liquid Track Winner: GalamseyWatch by @SAMADON_ 🇬🇭
A fine-tuned LFM2.5-VL-450M detects illegal mining across Ghana's forest reserves (4.8× pixel-IoU lift over base). An LFM2-2.6B tool-calling policy then decides, per tile: downlink_now, flag_for_review, request_higher_resolution, or discard — reasoning over bandwidth budget, cloud cover, and neighbor tiles.
The satellite sends a decision, not a tile.
youtube.com/watch?v=mfKrhjyB…
3
1
11
883
Our “AI in Space” hackathon, with @DPhiSpace, asked builders: What becomes possible when state-of-the-art models run in orbit?
The hackers that joined us really delivered, and we’re proud to announce the winners today: GalamseyWatch, by @SAMADON_ 🇬🇭, and Parali, by @kumar_munish_ and Aashish Kumar 🇮🇳.
Here’s what they built:
1
7
26
2,991
Samuel Donkor retweeted
New year, same intensity:
47
5,177
53,942
1,007,041
4 Dec 2025
nice bait tho. this is just Cunningham's Law. post the wrong answer and everyone appears out of nowhere to correct you
4 Dec 2025
i have a PhD in maths from the university of cambridge and i can’t solve this
115
29 Nov 2025
Our submission to the @cactuscompute @nothing @huggingface hackathon
Lucid bridges your digital world (email, calendar, tasks, notes etc.) with your physical environment using AR spatial memory, voice-first interaction and on-device AI
3
3
135
4 Dec 2025
Excited to share that our team placed 2nd at the Cactus (YC S25) x Nothing x Hugging Face Mobile AI Hackathon.
We were up against teams from MIT, Stanford, and builders from around the world. Grateful to have had the chance to build and compete alongside so many talented people.
1
3
425
4 Dec 2025
Answer: 🦜 = 15
🙎🏽♂️ = ( 🦜 170 )
🦜 = (200 - 🙎🏽♂️ )
🦜 = 200 - (🦜 170)
🦜 = 200 -🦜- 170)
2🦜 = 200-170
2🦜 = 30
🦜 = 30/2
🦜 = 15
4 Dec 2025
i have a PhD in maths from the university of cambridge and i can’t solve this
185
12 Nov 2025
“Ideas are easy. Execution is everything.”
11 Nov 2025
Never procrastinate your ideas. I had this same concept in 2022 called Urban Moon and I kept procrastinating until I never executed. If you have an idea today, try your very best and bring it to live
2
157
Samuel Donkor retweeted
7 Nov 2025
Announcing Speech Recognition and Generation from @KhayaAI for 32 African Langs covering ~540 million people!! Live demo in comments.
See video for demo of Speech Recognition for Southern Ghanaian Langs.
@KhayaAI is the only AI covering all government sponsored Ghana langs 🔥
113
1,125
3,106
158,795
24 Oct 2025
Spent the weekend optimizing afriSpeech-whisper-medium for mobile inference.
The base model is 2.8 GB which is way too large for mobile devices. So I converted it from PyTorch to GGML format, creating three compressed versions:
Q8_0: 786 MB (72% reduction)
1
46
24 Oct 2025
There's a "Goldilocks zone" in quantization where you balance size, speed, and accuracy.
Next, I tried fine-tuning the model using intronhealth/afrispeech-dialog. Turns out it only had 49 samples, basically just 3 training batches for a 769M parameter model.
1
27
24 Oct 2025
The output was complete gibberish.
So I found a better dataset: intronhealth/afrivox with 18,881 samples and 64 hours of audio. Currently waiting for access since it's gated, but my training pipeline is ready to go.
26
16 Oct 2025
Bscribe helps clinicians spend less time on paperwork, and more time with patients.
It captures clinical conversations, generates structured, evidence-based notes, and syncs directly with your EMR.
Join the beta today.
bit.ly/BscribeAI
1
22
16 Oct 2025
Bscribe helps clinicians spend less time on paperwork, and more time with patients.
It captures clinical conversations, generates structured, evidence-based notes, and syncs directly with your EMR.
Join the beta today.
bit.ly/BscribeAI
3
46
Samuel Donkor retweeted
16 Oct 2025
"am i actually a fit for this?"
it's hard to answer when applying for a @ycombinator startup or @Starbucks barista
so we made a 5min reality check
that roasts you in the process
👉 howuselessareyou.com
ps. there's a leaderboard. if you're first, you're last.
5
3
20
670
6 Oct 2025
Announcing Bscribe's private beta. Doctors spend 2-3 hours every day on paperwork. After seeing 30 patients, there's still hours of documentation ahead. We built Bscribe to give you that time back. Request access: bscribe-nine.vercel.app
3
55
6 Oct 2025
Announcing Bscribe's private beta
Doctors spend 2-3 hours every day on paperwork. After seeing 30 patients, there's still hours of documentation ahead.
We built Bscribe to give you that time back.
Request access: bscribe-nine.vercel.app/
36