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.
ELON: THE PROBABILITY OF MECHAZILLA CATCHING STARSHIP IS ABOVE ZERO
“It'll weigh about 250 tons.
We'll make that lighter over time.
So, you got a couple of hundred tons plummeting more than half the speed of sound.
So, this thing is still coming in really fast.
Pretty much down in a downward direction.
So then, they light the engines, so it's got to slow itself down very fast and correct any errors.
Whatever the X-Y error is when the engines land, it's got to take out that X-Y error and then drop the velocity to basically zero, come in between the arms.
The arms will be wide, and as it's coming in, the arms will close, go flush against the side of the vehicle, and the vehicle will be descending through the arms.
And those tiny little, you can barely see them, the little knobs, those kinds of lifting lugs will touch the top of the arms, and then it will hopefully not shear off and crumple.
Success is one of the possible outcomes.
The probability is uncertain, but it is above zero.”
Source: @elonmusk, @Erdayastronaut, May 2022
Are You Seeking to Build the Right Cloud Infrastructure for Your Business? ☁️🚀
Join our webinar to get answers to questions on:
✅ Scalability
✅ Control
✅ Cost Efficiency
✅ Real-World Deployment Scenarios
Introducing GPT-4o, our new model which can reason across text, audio, and video in real time.
It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):
I’m not going to pretend to have technical experience with DevOps, but I certainly have experience paying cloud bills. @pipeopshq is a very robust platform and sometimes I wonder how we are able to keep our cloud cost so low; well, I don’t exactly wonder, @nitrocode is my CTO.
While speaking with other founders, I found that some products that are seemingly less complex have almost 2x our cloud bill, that's absurd. Nevertheless, I have good news, we’ve put together this event to share practical real-world steps you can start to explore now to reduce your cloud cost, and I can’t think of better people to speak on this subject than @nitrocode and @nimboya
Registrations are currently open here: https://t.co/lZvSJoJmhN, we are also throwing in a free E-book on 9 simple steps you can take to start reducing your cloud cost when you register.
If you want a fresh POV to look at your cloud infrastructure from you don’t want to miss this.
#Cloudcosts #Cloudbills
I’ve been silent for a while on the conversation of Nigerians having to pay their cloud costs in dollars, I’ve highlighted 2 main issues,
🌟Inconsistent Billing
🌟Exorbitant costs
It's quite easy to figure out the cause for inconsistent billing, of course, our wonderful forex situation.
Also, cloud costs can escalate, really fast. There was a time when we didn't deploy to the cloud - we used cheaper and less efficient servers. But now, it has become super easy to spin up >$500 in monthly cloud bills. Some can extend even up to multiples of this monthly.
Google Cloud Platform (GCP), Amazon Web Services (AWS), and Microsoft Azure are some of the top contenders. Then we have Vercel, Netlify, Heroku, and DigitalOcean in the next level space. One thing they all have in common? They charge you in USD.
When thinking around this problem, we didn’t just want to allow users to “pay in Naira”, the challenge was providing a solution that kept cost as minimal as possible, but also streamlined the experience of setting up, managing, and deploying to the cloud. In Nigeria, as the dollar gains against the Naira, it's greatly inconvenient to pay in dollars every month.
Well, with the rollout of our Nova Servers, we will allow you to create servers that are deployment-ready out of the box and you can conveniently pay in Naira. Coupled with our stellar deployment experience, we will easily become your go-to solution for going live on the cloud without significant cloud expertise.
If you join our list of startup founders interested in this, you also get up to ₦75,000 in credits to get you started on @pipeopshq.
If this sounds useful, sign up here before it ends.
https://t.co/GAMPwD1BTN
Welcome to the future of VR with Disney's HoloTile.
The system is comprised of hundreds of small, round “tiles” that serve as a kind of mini, omnidirectional treadmill.
Read all about HoloTile here: https://t.co/uqlrXZLsht
Today, I stepped down as CEO of Binance. Admittedly, it was not easy to let go emotionally. But I know it is the right thing to do. I made mistakes, and I must take responsibility. This is best for our community, for Binance, and for myself.
Binance is no longer a baby. It is time for me to let it walk and run. I know Binance will continue to grow and excel with the deep bench it has.
I’m pleased to announce that @_RichardTeng, our now former Global Head of Regional Markets, has been named the new CEO of Binance today.
Richard is a highly qualified leader and, with over three decades of financial services and regulatory experience, he will navigate the company through its next period of growth. He will ensure Binance delivers on our next phase of security, transparency, compliance, and growth.
Prior to joining Binance, Richard was CEO of the Financial Services Regulatory Authority at Abu Dhabi Global Market (ADGM); Chief Regulatory Officer of the Singapore Exchange (SGX); and Director of Corporate Finance in the Monetary Authority of Singapore.
With Richard and the entire team, I’m confident that the best days for @Binance and the crypto industry lay ahead.
As a shareholder and former CEO with historical knowledge of our company, I will remain available to the team to consult as needed, consistent with the framework set out in our U.S. agency resolutions.
What’s next for me?
I will take a break first. I have not had a single day of real (phone off) break for the last 6 and half years.
After that, my current thinking is I will probably do some passive investing, being a minority token/shareholder in startups in areas of blockchain/Web3/DeFi, AI and biotech. I am happy that I will finally have more time to spend looking at DeFi.
I can’t see myself being a CEO driving a startup again. I am content being an one-shot (lucky) entrepreneur. Should there be listeners, I may be open to being a coach/mentor to a small number of upcoming entrepreneurs, privately. If for nothing else, I can at least tell them what not to do.
On that note, I am proud to point out that in our resolutions with the U.S. agencies they:
- do not allege that Binance misappropriated any user funds, and
- do not allege that Binance engaged in any market manipulation.
Funds are SAFU!
With that, I look forward to seeing the new leadership take the reins. Please join me in congratulating Richard on his well-deserved promotion.
Onwards!
CZ