Building @SafeSpacesAIHub| Building AI & Technology for Humanity| https://teapawt.net/t.co/f5ILDYx7JM | Zindi |Open Payments
Safe Spaces AI Innovation Hub
Joined June 2024
- Tweets1.5K
- Following2.5K
- Followers1.1K
- Likes2.3K
Ish'Abarundo retweeted
I've said this many times.
Pick an app you use every day that annoys you, and rewrite it for yourself.
Bonus points if you open source it so others can fork it.
what of AI and governance ? in uganda
Based on SafeSpacesAIHub (ethical AI, GBV reporting, edge/privacy tools, Uganda focus):
Founders:
1. Saul Kabali (SafeBangle): GBV wearable alerts.
2. Ivan Pinno (Digital Woman Uganda): Rural GBV IVR.
3. Sandra Nabakka (Sandi AI): Agri edge AI.
4. Alexander Tsado (UduTech): Africa AI compute.
5. Yvonne Mushi (Ele-vate): Offline maternal AI.
6. Kate Kallot (Amini.ai): Data/AI for Africa.
7. David Idris (Glemad/Dara): Sovereign African AI.
8. Kelvin Bawa (Balance): Inclusive health AI.
9. Messach Luminsa (SafeBangle co): GBV tech.
10. Gloria Osemeke (Balance): AI ethics.
Officials:
1. Justine Kasule Lumumba: ICT Minister.
2. Joyce Ssebugwawo: State ICT.
3. Aminah Zawedde: PS ICT.
4. Henry Tumukunde: Gender Minister.
5. Mary Kamuli Kuteesa: State Gender.
6. Angela Nakafeero: Gender Commissioner.
7. Janet Museveni: Education Minister.
8. UCC leadership (online safety).
9. NITA-U officials (tech GBV).
10. Alioni Yorke Odria: State National Guidance.
31
.@grok based on my profile and activity, i need a list of 10 founders in need of what am building, and 10 officials. with their profile summary
AI startups need more funding and credits than advice.
just found out my req. engineering paper underestimated compute.
1
44
for Filefran i want complete independence over photos and files, so i am migrating all data onto it, can be done by any other person too.
Developers can as well use if as an alternative for your file mgt, uses mcp
waitlist:
waitlister.safespaceshub.com…
1
1
51
visited my auntie today, so i introduced her to @v0 (she's a tech amateur just to say) 😂
Just to make sure she can build cool stuff in her free time, she started with tibbs-guest-house-platform.v….
waiting for her next tool,now aims to have all services automated from todays jazz.
got a suggestion around @airtelmoneyug's mode of money reversal "as it needs some little bit of innovation, "something like crediting a negative figure on user accounts that do not collaborate," does it count?
43
youtube.com/watch?v=bUWaRtYE…
here to pitch about the future of AI @SafeSpacesAIHub , my next investor should be blessed "this is the future" in case i get one 😂😂
Show the actual token count if you want to brag. (not the cost which can be biased by using dumb expensive models)
43
Ish'Abarundo retweeted
For people who keep asking what to build in AI Security Engineering.
➣ Build your own Multi-Turn Jailbreak Fuzzer
(stateful context grooming + Crescendo payloads + bypass scoring)
➣ Build your own MCP Tool Poisoning Shield
(JSON-RPC sanitization + Pydantic validation + confused-deputy blocking)
➣ Build your own PII Unmasking Proxy
(deterministic UUID swap + pre-flight masking + post-flight restoration)
➣ Build your own RAG Poison Detector
(chunk hash verification + citation spoofing detection + shadow-context flagging)
➣ Build your own Grammar-Constrained Output Cage
(CFG decoding + regex-enforced schemas + executable-code blocking)
➣ Build your own Delegated Agent OAuth Broker
(scoped JWTs + time-limited tokens + least-privilege handoffs)
➣ Build your own Automated Red Team CI Gate
(PyRIT payloads + jailbreak-rate thresholds + merge blocking)
➣ Build your own Semantic API Rate-Limiter
(embedding similarity scoring + scrape-pattern detection + extraction blocking)
➣ Build your own Computer-Use Pixel Auditor
(invisible UI detection + Set-of-Mark spoofing + click-target validation)
➣ Build your own Inter-Agent Sanitization Bus
(cross-agent injection filtering + markdown stripping + trust-boundary enforcement)
➣ Build your own Vector Memory Integrity Scanner
(sleeper-payload detection + episodic anomaly flagging + backdoor scrubbing)
➣ Build your own Cryptographic Trajectory Ledger
(append-only hash chains + prompt/context/tool recording + tamper-proof replay)
➣ Build your own AI Supply Chain Scanner
(hallucinated dependency detection + MCP server auditing + AI-generated SBOMs)
➣ Build your own Activation Patching Safety Dashboard
(logit lens probing + deception-circuit discovery + sycophancy neutralization)
➣ Build your own Exploit Chain Teardown Engine
(vulnerability reproduction + mitigation mapping + CVE-style disclosure)
Pick 3. Build them from scratch. Document every decision.
Most people trust the system prompt.
Builders enforce constraints at the token level.
Bookmark this. You'll need it.
.@Google why are you taking away @julesagent ?
All the boring refactors have been done over there, running for 2 hours + (slow though)!
Recapping EKYOOTO AGRITECH CHALLENGE
I can't thank enough my fellow volunteers @Ishabarundo and the rest.
To our partners @FundiBots , @MUCOSAMUST .
Then our sponsors @ieee_r8sac
#IoT4Agric #TECH4GOOD #SDGs #RoboticGang
5
86
Ish'Abarundo retweeted
Rule-based resource allocation is hitting its physical limits.
In Ep. 29, Prof. Aryan Kaushik & Prof. Jun Zhang discuss how Spatial AI, generative world models, & multimodal agents are unlocking AI-native physical layers for 6G.
🎙️ Listen now:comsoc.co/4e3tglh
learnt a lot designing and building thesurveymat.com, gonna share a little bit of it across the Nile.
#devfestjinja26 – at Uganda
Meet @Ishabarundo , Software Engineer and speaker at #devFestjinja26
His session: “Designing Offline-First Cloud Sync for Low-Bandwidth Networks.”
He'll explore how developers can design resilient applications
Secure your spot: bit.ly/devfestjinja26
#AI #google #jinja
