Amir Hesham

2.8K posts

Amir Hesham banner
Amir Hesham

Amir Hesham

@someshowman

Katılım Mayıs 2018
388 Takip Edilen903 Takipçiler
Sabitlenmiş Tweet
Amir Hesham
Amir Hesham@someshowman·
yeah we did it
Amir Hesham tweet mediaAmir Hesham tweet media
English
10
5
2.3K
85.5K
Amir Hesham retweetledi
le.hl
le.hl@0xleegenz·
Walking alone through a foreign city at night and realizing how far you’ve come has to be a top 3 peak moment of all time
English
937
22.6K
110.2K
18.9M
Amir Hesham
Amir Hesham@someshowman·
حار مات صيفًا، دايخ ممطر شتاءً
العربية
0
1
5
363
Amir Hesham
Amir Hesham@someshowman·
2026 is my best year so far, with even better stuff lined up. Super grateful. الحمدلله
0
0
11
315
Amir Hesham retweetledi
Greg Brockman
Greg Brockman@gdb·
Software development is undergoing a renaissance in front of our eyes. If you haven't used the tools recently, you likely are underestimating what you're missing. Since December, there's been a step function improvement in what tools like Codex can do. Some great engineers at OpenAI yesterday told me that their job has fundamentally changed since December. Prior to then, they could use Codex for unit tests; now it writes essentially all the code and does a great deal of their operations and debugging. Not everyone has yet made that leap, but it's usually because of factors besides the capability of the model. Every company faces the same opportunity now, and navigating it well — just like with cloud computing or the Internet — requires careful thought. This post shares how OpenAI is currently approaching retooling our teams towards agentic software development. We're still learning and iterating, but here's how we're thinking about it right now: As a first step, by March 31st, we're aiming that: (1) For any technical task, the tool of first resort for humans is interacting with an agent rather than using an editor or terminal. (2) The default way humans utilize agents is explicitly evaluated as safe, but also productive enough that most workflows do not need additional permissions. In order to get there, here's what we recommended to the team a few weeks ago: 1. Take the time to try out the tools. The tools do sell themselves — many people have had amazing experiences with 5.2 in Codex, after having churned from codex web a few months ago. But many people are also so busy they haven't had a chance to try Codex yet or got stuck thinking "is there any way it could do X" rather than just trying. - Designate an "agents captain" for your team — the primary person responsible for thinking about how agents can be brought into the teams' workflow. - Share experiences or questions in a few designated internal channels - Take a day for a company-wide Codex hackathon 2. Create skills and AGENTS[.md]. - Create and maintain an AGENTS[.md] for any project you work on; update the AGENTS[.md] whenever the agent does something wrong or struggles with a task. - Write skills for anything that you get Codex to do, and commit it to the skills directory in a shared repository 3. Inventory and make accessible any internal tools. - Maintain a list of tools that your team relies on, and make sure someone takes point on making it agent-accessible (such as via a CLI or MCP server). 4. Structure codebases to be agent-first. With the models changing so fast, this is still somewhat untrodden ground, and will require some exploration. - Write tests which are quick to run, and create high-quality interfaces between components. 5. Say no to slop. Managing AI generated code at scale is an emerging problem, and will require new processes and conventions to keep code quality high - Ensure that some human is accountable for any code that gets merged. As a code reviewer, maintain at least the same bar as you would for human-written code, and make sure the author understands what they're submitting. 6. Work on basic infra. There's a lot of room for everyone to build basic infrastructure, which can be guided by internal user feedback. The core tools are getting a lot better and more usable, but there's a lot of infrastructure that currently go around the tools, such as observability, tracking not just the committed code but the agent trajectories that led to them, and central management of the tools that agents are able to use. Overall, adopting tools like Codex is not just a technical but also a deep cultural change, with a lot of downstream implications to figure out. We encourage every manager to drive this with their team, and to think through other action items — for example, per item 5 above, what else can prevent a lot of "functionally-correct but poorly-maintainable code" from creeping into codebases.
English
414
1.6K
12.2K
2.1M
Amir Hesham retweetledi
Andreas Storm
Andreas Storm@avstorm·
Apple TV’s colorful new branding was built with glass and captured in-camera.
English
271
2.3K
23.7K
3M
Mogzz
Mogzz@Eyadelmogy·
“The courage to be happy also includes gyhe courage to be disliked “
English
2
1
72
9.6K
Amir Hesham retweetledi
DHH
DHH@dhh·
@shrisha4real Omarchy doesn't need money. We make it for the love of computers.
English
42
50
2.2K
65.5K
kenneth
kenneth@kennethnym·
convex + jotai + tanstack + bun is such a comfy webdev combo (jotai is criminally underrated)
English
21
5
274
25.7K
Amir Hesham
Amir Hesham@someshowman·
@Sherif2602 العياط بييجي مع التغيير كدة كدة
العربية
0
0
1
82
SDS
SDS@Sherif2602·
@someshowman مينفعش تحاول تغير وبعدين تقعد تعيط شوية؟
العربية
1
0
1
119
Amir Hesham
Amir Hesham@someshowman·
@bassiounix @AhmedGhazey انت صح، للاسف انا كنت بحب تويتات احمد بس واضح ان ال superiority complex غلبته و مخلياه مش عايز يفهم رأيك وبي discard رأيك ب "كلامك طموح و جميل"
العربية
0
0
3
172
Muhammad Bassiouni
Muhammad Bassiouni@bassiounix·
@AhmedGhazey مفيش خلاف على كلامك ولكن انا مش قصدي تروح تعمل حاجة بحجم linux Micro kernel او اي حاجة صغيرة شبه xv6 هتبقي كافية انك تطبق بايدك على اللي اتعلمته
العربية
1
0
2
501
Amir Hesham retweetledi
Sahil Bloom
Sahil Bloom@SahilBloom·
Everyone needs to hear this…
Sahil Bloom tweet media
English
299
3.3K
22K
3M
Amir Hesham
Amir Hesham@someshowman·
@mustafasuleyman Yeah and also can fuel genocide. For some people, it literally means losing their future.
English
0
0
1
138
Mustafa Suleyman
Mustafa Suleyman@mustafasuleyman·
AI could fuel progress + prosperity for all - if we build it to serve people's needs. Seemingly Conscious AI is the antithesis of that, asking humans to serve its simulated needs. It could mean losing the better future AI was supposed to create.
English
68
13
154
29.5K
Amir Hesham
Amir Hesham@someshowman·
@eigenron One of my friends had the same issue and turns out he has almoplantar hyperhidrosis. Plz see a doctor
English
0
0
0
52
eigenron
eigenron@eigenron·
bro why the fuck are my hands so fucking sweaty all the fucking time? i'm sorry midnight mac i'm really sorry i don't intend to do this to your beauty but i can't help it.
English
3
0
3
645
Amir Hesham
Amir Hesham@someshowman·
Never been a better time to be a beginner. Experienced engineers find building software with Agentic/LLM components scary because it challenges their years of cultivating deterministic logic. Rewire your brain and embrace non-deterministic systems.
English
0
0
2
263
Oliur
Oliur@UltraLinx·
@dannypostma Going there end of this month. Looking forward to it.
English
3
0
15
2.9K
Pontus Abrahamsson — oss/acc
Customizable widgets for what's most important for your business. Click to explore deeper in the assistant.
English
10
1
115
7.1K
Amir Hesham
Amir Hesham@someshowman·
My boys and I are going places and I’m so proud of us.
English
0
0
9
600