Ramitha Daniel

~a technology enthusiast~

[Ramitha Daniel @RamithaDaniel]

@shanaka86 @grok summarise this

[Ramitha Daniel @RamithaDaniel]

@steipete @Dudi4Israel @openclaw It’s getting a bit frustrating tbh seeing how many times you have to repeat this. For anyone wondering if OpenClaw was sold to OpenAI, please go watch the podcast with Lex Friedman on yt. OC being opensource was a hard condition from the start of negotiations . Sigh

[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.

[Dr. Alex Wissner-Gross @alexwg]

https://t.co/zpW49yG4CR

[Ramitha Daniel @RamithaDaniel]

@DrBukkabwoi Bloody jokers men

[Ramitha Daniel @RamithaDaniel]

@DrBukkabwoi @anuradisanayake Lets hope he walks the talk!

[Ramitha Daniel @RamithaDaniel]

@caderacm @aruwij @RW_SRILANKA What did you expect buddy? A plasma tv?

[Ramitha Daniel @RamithaDaniel]

https://t.co/j3uAcivGOd has to one of the shittiest platforms of the century. It’s a miracle if you can login to their platform.
Utterly frustrated!
@VFSGlobal @vfsglobalcare

[Ramitha Daniel @RamithaDaniel]

🙌

[Home Assistant @home_assistant]

Today we are pleased to announce that we're joining the Z-Wave Alliance! Check out how we're making it easier for companies to develop Z-Wave controllers and grow the Z-Wave ecosystem with Home Assistant in the latest blog post. 👇🏻 https://t.co/VJQVYbbUVX

[Shruti @heyshrutimishra]

AI VIDEO is insanely taking over in 2024.

OpenAI just announced Sora , their first text-to-video model.

Here are 12 wild examples you can't afford to miss out on: 🧵

[Ramitha Daniel @RamithaDaniel]

Sora please! 😂

[kitze the 🐐 @thekitze]

woah sora is 🤯

“indie founder of a vr startup, white curtain background, waving hands, bashing competition without valid facts, vertical video shot on an android phone from 2017”

[Ramitha Daniel @RamithaDaniel]

🙌

[Home Assistant @home_assistant]

iOS users, it's here: CarPlay!
Update your app to the latest version to get CarPlay support. From your car you'll have easy access to your devices, areas, and custom actions you can create in the app. Check out our garage door demo and read the blog here:

https://t.co/geUXBR9X1V

[Ramitha Daniel @RamithaDaniel]

@phracka Yup, I preordered. Arrival time is July ‘24 🙌

[Ramitha Daniel @RamithaDaniel]

Super stoked to explore if and how the #RabbitR1 would integrate with #homeassistant

[Ramitha Daniel @RamithaDaniel]

Genuinely excited about the r1!

[Jesse Lyu @jesselyu]

if @MrBeast pick me then i'm gonna give 125 random people a free rabbit r1 that repost this and follow me for fun (the $25,000 offered from @MrBeast )

[Ramitha Daniel @RamithaDaniel]

@ShehanRG I’m on an M1 pro 🙈

[Ramitha Daniel @RamithaDaniel]

2 mins to download. 20 mins to extract 🤦‍♂️

[Ramitha Daniel @RamithaDaniel]

@ShehanRG Been using this for a while now. Pretty good so far

[Nishan Wijesinghe @swnishan]

I’m joining to this event. Are you guys ready?
https://t.co/HdeyuJQVa4

[Physics In History @PhysInHistory]

When Oppenheimer met Einstein:

"Einstein, who had witnessed the cataclysmic potential of this energy, was cautiously wary. He cautioned against the unbridled release of such power, fearing its devastating consequences. Oppenheimer, however, saw a glimmer of controlled potential — a path toward unlocking the secrets of the nucleus for the betterment of humanity."

Full Story @Medium : https://t.co/kyka5xxhfV
[Image: © Alfred Eisenstaedt/The LIFE Picture]