Today, AI is rapidly changing the way we build software, and the pace of that change is only accelerating. If our goal is to make programming more productive, then building at the frontier of AI and software feels like the highest-leverage thing we can do.
It is increasingly clear to me that Codex is that frontier. And by bringing Astral’s tooling and expertise to OpenAI, we’re putting ourselves in a position to push it forward. After joining the Codex team, we’ll continue building our open source tools, explore ways they can work more seamlessly with Codex, and expand our reach to think more broadly about the future of software development.
You must log in or register to comment.
- siera@jlai.luEnglish1 day
The developers were already genAI users.
But now I fear that the tutorial will include an “openai init”, and other non-deterministic subscription-based commands for ruff and uv and that will be what is pushed.
- Axum@lemmy.blahaj.zoneEnglish13 hours
If all this does is fund astral and by extension
uvI don’t see a problem here.Hell, I’d take ai Corp money to fund making good tools for the community, as it’s one less stack of cash being used on bullshit datacenters.
1 dayFFS, first Bun, now Astral… It’s a shame, uv is such a useful tool in the Python ecosystem.
- prism@lemmy.dbzer0.comEnglish1 day
Sigh. I knew uv and ruff were too good to be true. Just hope the community can fork before it all goes to crap.
- siera@jlai.luEnglish1 day
But which form will survive ?
I want tools from the python foundation ! (I kinda hoped ruff and UV were taken over by the pypa)
- Axum@lemmy.blahaj.zoneEnglish13 hours
UV is open source.
Dont gaslight yourself thinking it’s suddenly going to kill your grandmother now or something.
- 1 day
I find that Python requires a fair bit of discipline to keep it readable, and I’ve seen some very unreadable code written by people. Vibe coding with Python’s dynamic nature seems like a match made in hell.
- galaxy_nova@lemmy.worldEnglish1 day
This is true although that’s what enforcing strict type checking and good linting is supposed to help with. I think it’s partially an issue that you can kinda just type what you think and not everyone thinks efficiently/ programmer-y
Edited for clarity
- 1 day
Agreed! I think both linting and type checking are extremely important to Python, but it’s also an extra step that far too many people just don’t take. And honestly, I used to get tripped up sometimes with setting up Python tooling before I started using uv.
Unfortunately I also have to work with the occasional Python script that someone just slapped together, and that’s something far too easy to do in Python. It does kind of remind me of vibe coding. Initial velocity seems high, but if you’re not thinking about it, long term maintenance tanks.
That’s not to say Python is bad, and there is certainly a lot of good Python code out there too. But it’s a language that does make it easy to make a mess, which will probably be compounded by LLMs.
It’s manageable if you pass along these rules to the LLM. I’ve actually had more success asking the LLM than giving code reviews to some interns, and even someone who coded professionally before.
- badgermurphy@lemmy.worldEnglish3 hours
Right, but aren’t the interns in training specifically to get better at that than they are today, and eventually surpass the abilities of the AI?
These LLMs are at best OK at this stuff, and are not improving at any sort of convincing rate. If you don’t train anyone to be better than the LLM, the retirement of your generation will make the whole industry you’re in at best, OK at its job.
Ok, I’m not suggesting replacing humans with AI and I despise companies trying to do this unsustainable practice.
With that out of the way, I’ll restate that LLMs follow some rules more reliably than humans today. It’s also easier to give feedback when you don’t have to worry about coming across as a pedantic prick for pointing out the smaller things.
On your point that LLMs are not improving; well, agents and tooling are definitely improving. 6 months ago I would need to babysit an agent to implement a moderately complex feature that touches a handful of files. Nowadays, not as much. It might get some things wrong, but usually because it lacks context rather than ability. They can write tests, run them, and iterate until it passes, then I can just look at the diff to make sure the tests and solution makes sense. Again, something that would fail to yield decent results just in the last year.
- badgermurphy@lemmy.worldEnglish60 minutes
When I refer to improvements, I mean fundamental improvements to the underlying technology, which appear to be at a stubborn plateau.
I believe the improvements you’re referring to are better guardrails. They are still improving the interface with regard to context and scope, as those functionalities are separate from the underlying technology, bolted on top of it to keep it on task and more continually aware of and operating within the defined context.
Underneath, though, each new model appears to be a refactoring of the previous one to get different sometimes better results, but the methodology is the same, and its strengths and weaknesses remain largely unchanged.
So, essentially what my objection to this practice is this:
This technology has led to companies leaning harder on their current people to get more done with the same amount of time with AI tools. That doesn’t seem to be successful at any sort of scale so far, but that’s the plan nonetheless. As a result, new talent is coming into the industry at a much slower rate than before–hiring is on hold while everyone waits to see if these tools really can replace bodies in the workforce in a serious way (again, super inconclusive at this point).
So, looking forward even one single generation, we will have dramatically fewer experts in the field than before, because so many fewer people were able to start in that field last generation. Since the need for programmers is greater every year, either these tools will be a wild success and meet all these business demands, or there will be a crisis of demand with no easy ways out.
Since both of the foreseeable outcomes are detrimental to the workers themselves, what and who exactly are we rooting for? I think that most people, given the choice, would choose the existing cycle with a proven track record, rather than gamble on something so uncertain with no clear economic benefit to the workers themselves.
- 1 day
Hi, I’m an AI engineer based in Japan, and I’m expanding into the U.S. market to work with more long-term clients. I’m looking for an American collaborator who can act as a communication bridge between me and U.S. clients.
I will handle the technical side myself, including project planning, AI development, and software implementation. Your role would be to join meetings, help with smooth communication, and support the client relationship side.
If this sounds like a good fit, please send me a message.
