5x Hackathon winner | @tembo ambassador | AI Partner @Freepik | anyone can edit @clippityai

Joined July 2021
239 Photos and videos
Pinned Tweet
4 Sep 2025
I like posts, because I like them It's that simple (no growth hack here)
I highly recommend you start building a habit of liking more posts as you scroll the timeline It allows you to be in everyone’s notifications at once all while supporting the people in your network Once they notice you, they become more likely to engage back Easy growth hack
1
15
4,130
coderhema retweeted
Jun 13
You can now connect your SuperGrok subscription directly to the Warp Agent. Get access to the latest models, including Grok Build 0.1.
18
17
161
16,887
coderhema retweeted
Jun 13
Remember, open source models are only ~4 months behind now
179
171
5,779
280,695
coderhema retweeted
Woke up to the news of Anthropic blocking non-US citizens from accessing Fable 5. And it draws a strong parallel with something I read very recently in Martin Kleppmann’s popular book, Designing Data-Intensive Applications: political sanctions can mess up your business. Granted, he was referring to the downsides of cloud services, but it seems the same principle applies in this fast moving world of AI. You build your app on a model and wake up one morning to 404 errors because of an unforeseen political situation. Someone I follow on LinkedIn today talked about how it was very important for companies to start pivoting to open source models to avoid this kind of risks. While it does make sense, my question is: is it foolproof?
1
2
10
966
coderhema retweeted
The Nigerian government has done something impressive. They have convinced millions of people that struggling to eat, struggling to pay rent and struggling to survive is a personal failure instead of an economic one. That's genius.
163
5,334
11,969
113,681
coderhema retweeted
🚀 Looking for testers Webapp: byuld.vercel.app Breaking into Web3 can feel intimidating. BYULD helps builders learn while they build, making concepts, decisions, risks, and tradeoffs easier to understand. ⚠️ Best experienced on PC Feedback: forms.gle/EU5CouhXfj592tGeA
4
14
157
I have a Xiaomi who's screen got broken, I planned on fixing it back after exams and use it to run a mini server for my devices it's a 128 GB one I also have another device I'll had as a cluster with my present one This ages well hopefully, Welldone @Google
People replace their phones every ~4 yrs. This means there are hundreds of millions of old phones discarded each year that are still perfectly usable as computing devices. @Google in collabration with @UCSD is exploring how to turn these old phones into cloud-computing “phone clusters”. Putting phones back in service in this way can directly reduce the environmental footprint of computing by avoiding the need for further raw material extraction, and taking advantage of the embodied carbon already incurred from manufacturing these devices, and modern phones actually are already quite powerful computers. Read more in the blog below ⬇️
29
For the @Lovable | @meetgranola hackathon I built graphite studio (made the logo too) A simple app that converts your granola recordings or notes into Infographics, mindmaps and flowmaps Exports in PNG, SVG and MD graphitestudio.lovable.app
Submissions are now open: meetnmake.lovable.app
8
622
coderhema retweeted
Jun 13
When you rent your artificial intelligence, you have no control, and no choice. This is why sovereignty and ownership matters. Whether it means using your own hardware, open source, or deep customization. Own your AI, own your future.
44
207
1,491
122,868
coderhema retweeted
Get paid to wait The Claude Code spinner might be the most watched line on Earth. So I turned it into an ad marketplace. Advertisers bid on it. You keep 50% of the money. Install the extension → get cash from ads. Introducing Kickbacks
1,104
497
13,119
7,607,696
coderhema retweeted
It’s tiiimeeeeee! SpaceX is live on Bamboo📢
56
81
909
34,755
coderhema retweeted
Self-hosted n8n on my Aeroplane instance.
10
4
121
3,666
coderhema retweeted
say something nice about this if enough of you do we'll 3x Minimax M3 limits on OpenCode Go
119
11
836
63,409
coderhema retweeted
May 14
do you know you don't need to carry your laptop anymore? you can run multiple ai agents parallelly from your phone and it's 100% FREE and OPENSOURCE links in the replies :)
10
8
49
4,611
Very neat, running everything from my phone including opencode
May 14
if you are looking for something which lets u use more than just codex then you can checkout my app you can use codex, claude code, opencode and a lot more ai agents directly from your phone
22
Someone help me. There's this app like kittylitter that I asked if they have an Android version is for building with agents I forgot to try it fully
13
coderhema retweeted
If you’re Nigerian and you didn’t drop litter in your environment today, like & RT. I want to check something.
148
5,609
12,949
372,425
coderhema retweeted
One company trying to own the whole narrative of "we are the good boys, and we have the best models" is not This morning I started working on some high-quality educational material to try to tilt the balance to the other side. More open-weights, more open-source and more sovereign AI (that is the only way forward).
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!
11
11
166
19,106
Will do this
Replying to @JamiuBalogun15
Aeroplane is 100% free. You can get a server from Hetzener and install Aeroplane on it in less than 2 minutes to get a Vercel-like deployment platform.
26
coderhema retweeted
Replying to @JamiuBalogun15
Aeroplane is 100% free. You can get a server from Hetzener and install Aeroplane on it in less than 2 minutes to get a Vercel-like deployment platform.
1
4
114
coderhema retweeted
LiteParse, our open-source/Rust-based doc parser, runs so quickly that Claude Fable 5 doesn't think it's real 🔥 It is the fastest document parsing solution on the planet and a great choice for your AI document workloads. Check it out: github.com/run-llama/litepar…
LiteParse runs so fast that Claude Fable 5 doesn't think its real
12
15
242
25,919