Abdullahi

614 posts

Abdullahi banner
Abdullahi

Abdullahi

@Ableezz

checkout https://t.co/GFeZDNjKtH

Nigeria Присоединился Ekim 2022
460 Подписки24 Подписчики
dax
dax@thdxr·
@kokialgo @maria_rcks @neocph @uzairakrum @karthiknish @ashirwadsingh_ @rhacius @Ananth7e @nigadamus @diegodamval @0XB34RDYB0Y @Dan_VAlves @TanmayGoel442 @InnoboSJ @Burgess_33 @_kittylove3 @alexlcpereira @NeoReplicante @Ableezz @Jint3x @HareeshXAi @defyus @Nateemerson @andreafspeziale you guys caught ryan doing the macarena if you want your free month of OpenCode Go send an email to dax@anoma.ly subject line "Macarena" from the email you want access with
QAM
21
1
180
28.5K
Abdullahi
Abdullahi@Ableezz·
@thsottiaux Can I skipp the 5 hour limit and just use my weekly limits how ever I want, I probably can finish it in an hour with 5.5 😑. I think codex limits are wayyy diluted not like, when I started using codex I couldn't use up the weekly limits but now, I can finish it in an hour I feel
English
0
0
0
308
Tibo
Tibo@thsottiaux·
What should we improve in the Codex app. What's not delightful?
English
3.5K
57
2.6K
472.3K
Nagarani
Nagarani@SNagarani1419·
@garrytan Memory will be more valuable than intelligence
English
1
0
0
124
Garry Tan
Garry Tan@garrytan·
I think one underestimated thing when we look back on it was how useful it is to have your own personal brain and company brain in 2026 at the dawn of usable AGI AGI gives you the intelligence You still have to collect your personal context to get the real unlock
English
130
69
1K
66.3K
Kimkimely
Kimkimely@Kimkimely299483·
@sahouraxo #thankyoubibi Please finish Hezbolah. A group of tugs that have taken billions from Iran and are always ready to come kill civilians in protests. We 100% want to see Hezbolah come to its end.
English
5
0
3
527
sarah
sarah@sahouraxo·
Israel has dropped over 200 bombs on Lebanon in less than 24 hours — murdering more than 83 civilians. This is an American-backed, American-funded genocide.
English
801
11.5K
20.4K
1.4M
Abdullahi
Abdullahi@Ableezz·
@Kimkimely299483 @sahouraxo It's not even a Jewish thing anymore it's just that the very nationality that the Israelis claim just won't work and was never meant to work, and the solution y'all think is to kill your way into existence
English
0
0
1
27
Abdullahi
Abdullahi@Ableezz·
@Kimkimely299483 @sahouraxo the people living Nazi Germany were not so different, they all went along with the actions of the Nazi Germany and all went out of touch with reality
English
1
0
1
33
Abdullahi
Abdullahi@Ableezz·
@Kimkimely299483 @sahouraxo your statement is not even stupid, its just fascinating how blind people can become when they enjoy sooo much impunity and feel so untouchable, so much so that y'all can define "who is intended to die" and dismiss the people who actually SUFFER and DIE as a result
Alagbado, Nigeria 🇳🇬 English
0
0
2
33
Abdullahi
Abdullahi@Ableezz·
@arayush01 @ThePrimeagen Prime to me sometimes feels like the last line of defense against general psychosis 😂
English
0
0
1
51
A R Ayush
A R Ayush@arayush01·
@ThePrimeagen you were the last person i thought who would start looping with llms...ahhhhhhh
English
1
0
2
4.1K
ThePrimeagen
ThePrimeagen@ThePrimeagen·
Unironically I have created a program looping actually works for
English
40
3
690
102.9K
Abdullahi
Abdullahi@Ableezz·
@thdxr Software today lacks intention and purpose and UIs mostly feel dead and generic
English
0
0
0
88
dax
dax@thdxr·
with the explosion of startups it's clear there are no founders interested in doing consumer products it's at the point where running a bloated sales heavy operation is glorified but until this changes the general public will continue to hate tech more and more
English
99
34
754
49.7K
Abdullahi
Abdullahi@Ableezz·
@WhiteHouse Who reviews social media posts before they get approved to be published 😂😂
English
0
0
0
6
The White House
The White House@WhiteHouse·
We really saved America before GTA 6
The White House tweet media
English
8.6K
10.8K
91.9K
10.1M
Cursor
Cursor@cursor_ai·
We're launching code storage and git hosting. Origin gives teams and agents a place to host, review, and collaborate on code. Available this fall. Join the waitlist. cursor.com/origin-waitlist
English
581
1.3K
14.7K
5.6M
dax
dax@thdxr·
first 25 people to guess what he's doing here get free OpenCode Go for a month
dax tweet media
English
376
2
343
61.8K
Abdullahi
Abdullahi@Ableezz·
@elonmusk That is the most impractical choice you could make, why tf
English
0
0
0
31
Homeland Security
Import the third world, become the third world. Thank you for your attention to this matter! 🇺🇸
Homeland Security tweet media
English
3.1K
7.8K
44.6K
1.2M
Abdullahi
Abdullahi@Ableezz·
@DHSgov Amazing 👏🏾👏🏾👏🏾
English
0
0
0
3
Abdullahi
Abdullahi@Ableezz·
@mitchellh Always great hearing your own specific opinion on working with these agents, will definitely try to follow this pattern
English
0
0
0
636
Abdullahi ретвитнул
Mitchell Hashimoto
Mitchell Hashimoto@mitchellh·
My heuristic is that any diff an agent generates over ~1500 lines is too big and is indicative that the problem needs to be decomposed. This is my general pattern now for feature work: 1. Try to implement the whole feature, loosely guided. I call this the "draw the owl" prompt in reference to the meme. Expect garbage, you're going to get garbage. 2. If the diff is less than 1500 lines, review it and iterate normally. If the diff is more than 1500 lines, prompt the agent to decompose the problem into atomic, incremental, reviewable tasks. Simultaneously, do this yourself. 3. Agents will very often make these tasks way too specific to the shape they solved. You need to massage it into the right general shape. Do that. 4. Kick off new agents to work on those incremental things (as parallelized as possible). Apply the same rules. 5. At a certain, point, repeat the "draw the owl" prompt. At some point, you will get beneath your review-ability threshold. This has been producing consistently high quality, maintainable, reviewable chunks of code that have a good handoff to either merge as-is or human refinement. And with the latest frontier models at xhigh thinking, these are all slow enough that you can usually have multiple going concurrently while you are actively reviewing others or working on your own tasks. HITL (human-in-the-loop) agents are still super important, especially for feature work. Features touch the human boundary in terms of UI, API, etc. And net new stuff can introduce pathologies in the architecture that violate desired invariants (these should be represented in specs or tests but we aren't perfect!). I know a lot of the leading edge agentic discourse is about "loops" and agents driving agents continuously. I do some of that (will report on that later). But, in terms of raw daily get-shit-done type of work, this is my most rewarding pattern at the moment.
English
97
232
3.7K
206.8K
Abdullahi
Abdullahi@Ableezz·
@thdxr Most probably someone in the C-suite of Anthropic has close contact with someone in the WH
English
0
0
0
1.6K
dax
dax@thdxr·
so how does "the white house contacted anthropic" work do they call them on the phone? what phone is it a landline?
English
189
16
2.5K
217.8K
Abdullahi
Abdullahi@Ableezz·
@thdxr The safety argument is definitely becoming a play/shield for monopoly, "others/open source should be regulated not us"
English
0
0
0
153
dax
dax@thdxr·
every time opencode gets posted on HN there's all these idiots who complain about me being mean to anthropic like i have some extremist viewpoint ben is extremely reasonable, very smart and this article understands the ecosystem better most of what i read and he's concerned
dax tweet media
Stratechery@stratechery

Anthropic's Safety Superpower Anthropic's belief in its own commitment to safety gives the company license to aggressively favor its business and even challenge the U.S. government. stratechery.com/2026/anthropic…

English
38
54
727
66.3K