Abdullahi (@Ableezz) header
Abdullahi (@Ableezz) profile picture

currently building e-commerce for agents @ https://teapawt.net/t.co/Q1fDC9x2ma

Nigeria
Joined October 2022
Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)Photo by Abdullahi (@Ableezz)
just shipped JustDrive it helps you move files between your machines with Google Drive, right from your terminal if you are the type with setups on different vps you know the pain of having to find a way to share data/files accross those machines here drive.astexlabs.com
2
1
2
67
F I N A L I S T S 🦅🇳🇬🇳🇬🇳🇬🇳🇬🇳🇬🇳🇬🇳🇬🇳🇬🇳🇬
197
1,767
160
8,841
174,596
💪🏾💪🏾
Nigeria are #U17WWC finalists! 🇳🇬

23
Abdullahi retweeted
BREAKING: PHONE ROBBED FROM SOWORE’S TEAM DURING BRUTAL ATTACK TRACED TO GOVERNOR’S LODGE IN ADO-EKITI! One of the phones stolen from a member of our team during Friday’s brutal attack in Ado-Ekiti has now been traced to the Governor’s Lodge in Ekiti State. The @PoliceNG and @OfficialDSSNG must immediately release the CCTV footage from Tawakalitu Restaurant to the public. You cannot bury the evidence.
243
837
64
2,009
449,403
Abdullahi retweeted
BREAKING: Google just proved AI data centers in space actually work Project Suncatcher's first satellite, built with @planet and launched on a SpaceX rocket with 4 TPUs on board, verified the physics: Google sent a prompt from Earth, a TPU in orbit ran Gemma inference, and the full answer was beamed back down. SpaceX is launching its StarMind satellites with NVIDIA GPUs on Starship in late 2027. Kardashev Type II civilization INCOMING
265
817
178
6,204
1,643,135
Abdullahi retweeted
We have been brutally attacked and injured by well armed government-sponsored thugs in Ado-Ekiti, Ekiti State. The @OfficialDSSNG provided these attackers with our exact location, enabling them to carry out this vicious assault. We won’t back down! We have a country to liberate!
535
535
61
2,028
160,937
Do you remember when you joined X? I do! #MyXAnniversary
1
10
deepseek harness is flat-out insane, no other even come close
1
28
...the cache hit rate is crazy 99%
11
Abdullahi retweeted
Replying to @rauchg
okay, lets do one better roadster-silk.vercel.app/
1
1
1
112
Abdullahi retweeted
The world stands at a crossroads. Despite extraordinary progress driven by cooperation and shared purpose, we face unprecedented backsliding on child rights, gender equality, international law and investment in children. Today, we ask world leaders at #UNGA: What kind of future will you choose to build for children?  unicef.link/4gsOOYy
14
69
5
178
49,536
There is a certain feeling of interest/confidence u get when reading any text that was written before the era of gen-ai. Now I have to read everything with way more skepticism that I probably won't even allow myself to enjoy reading whatever piece it is
37
dont believe the TMB benchmarks; using the model day to day will show you exactly where those 27B params fall short (and not even close) Dont compare possibly a Trillion+ parameter model like Opus 4.6 to a 27B just because of benchmark numbers
That's crazy when you think about it Qwen 3.8 27B is smarter than Opus 4.6 which was the absolute best model you could use 6-7 months ago. And now we have this Bonsai 2 retaining 98%+ of its intelligence... While weighing ONLY 5.9 GB 🤯 Intelligence density is absolutely crazy. Everyone has frontier intelligence at home now.
1
56
Abdullahi retweeted
PUBLIC NOTICE: AAC PARTY IS NOT PART OF ANY SINGLE-CANDIDATE COALITION TALKS LED BY PROF. @UtomiPat I have read a report in The Punch Punch Newspapers stating that a Political Commission led by Prof. Pat Utomi intends to hold talks with several presidential candidates, including myself, with the objective of producing a single opposition presidential candidate for the 2027 election. For the avoidance of doubt, neither I nor the African Action Congress (@AACParty) is part of these talks, and we will not be joining any such coalition. Our position is clear and principled. The AAC represents a fundamentally different political and ideological direction. Our revolutionary agenda is driven by ideological clarity, not political convenience, elite horse-trading or desperation for access to power. We cannot enter into a coalition with the same political establishment we have consistently opposed. Many of the politicians now presenting themselves as an “alternative” have, at different times, operated within the same political order, across the APC, PDP, Labour Party and other formations, that we know has failed Nigerians. Our opposition is not merely to Bola Ahmed Tinubu @officialABAT or the evil All Progressives Congress party @OfficialAPCNg . It is to the political system and governing practices that have produced decades of poverty, corruption, inequality, insecurity and underdevelopment. The @aacparty is offering Nigerians a different path: a revolutionary break from the old order and a program founded on social and economic justice, equal rights, accountable government, and the redistribution of political and economic power to the Nigerian people. We will not abandon that program for an arrangement whose principal objective is simply to replace one set of establishment politicians with another. The AAC is different. We know what we stand for, and we know the Nigeria we are fighting to build. We are not part of these coalition talks, and we will not be joining them. Omoyele Sowore Presidential Candidate, African Action Congress (AAC) #Sowore2027 #AAC #TakeItBack
330
165
30
475
48,860
Abdullahi retweeted
DEFEND MANKIND. JOIN THE DOMINION. STARCRAFT. 2030.
1,645
5,433
2,202
36,088
5,795,423
...
Not only I am tired of these wild AI speculations of impeding doom from self important people: I resent them. I actively resent people proposing to crash the economy or proposing authoritarian control over my life and other people's lives with idiotic and dangerous ideas like chip control or bans or tracking researchers. Every idiot in history who's taken the approach of "the ends justify the means" to solve an imaginary future disaster created the very disaster they wanted to stop. See Population Bomb leading to the one child policy and Communism leading to Mao's mass famines and Fascism leading to the death of tens of millions of people and war. These solutions are evil and worse than any disease that they propose to solve. It you believe you can actually predict the end of the world then you are as insane as the Heaven's Gate cult that killed themselves in the 90s thinking UFOs were coming to transcend them. Not only should we not take your policies and fear mongering seriously, we should actively throw out any and all of your proposed solutions because they come from a place of delusion. I don't give a shit that you work in the industry or think you saw something or that you want to virtue signal on X. You are actively contributing to a horrible future based on baseless speculation that has no grounding in reality. Don't confuse expertise in a domain with ability to predict impact of that domain or frankly to make predictions a decade out better than a dart throwing monkey. They are orthagonal skills. How's Hinton's "we don't need to train Radiologists anymore" working out? How did the Population Bomb work out? The global cooling second ice age? Peak oil? Just because someone is a bridge engineer does not mean they can predict the impact of bridges on society or that they have any actually useful insight at all on the complex, ever changing system called life. There are people dying in wars right now. Children starving. Homelessness. Dictatorships. In short, real problems. And we're supposed to drop everything to stop a made up problem in your head? Pound sand. We don't care. And we are not going to remake society based on you scary monsters under the bed delusion.
1
45
There are a lot of things wrong with this world… but too much intelligence is not one of them.
53
454
35
2,906
341,211
In other words, your company's bills is about to go thru the roof, I believe the approach 1 he mentioned is still the best, and if a dev can't deliver approach 1 why hire them in the first place, how did they even got hired
Replying to @bcherny
Hey ████, I think there is room for both. 1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking is low, it doesn’t need to be perfect. 2. Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. Luckily, the model makes it increasingly easy to do these well — run a few daily routines, use Claude Code Review, etc. Your job is to hold the bar on code quality. If Claude’s code doesn’t meet the bar, try: - Using the latest frontier model (Opus 5 or Fable 5.1) - Increase effort to high or xhigh - Invest in your CLAUDE.md and skills to succinctly teach Claude how to work in your codebase If all else fails, steer Claude more when you work with it, or have Claude fix accumulated debt and rewrite your codebase to make it easier to work with. Or, wait for the next model. Best, Boris
1
1
56
until it is cheap to set up all these elaborate workflows, option 1 is still the only economically viable option; vibecode all you want to test out ideas with cheap models create multiple work trees multiple agents try out same ideas with slightly different throwaway variations
20