Hanyu retweeted
Congrats to the What Would Jev Do? winners: Sandeep Manoharan, Kai John-Blunch and @queryverse_hy.
Three real builds with Jev and AdaL, from spotting rental scams to safer AI companions.
Watch each one in their own words.
Three real builds with Jev and AdaL, from spotting rental scams to safer AI companions.
Watch each one in their own words.
0
1
4
313
Well said
I’ll try to disagree with this without calling BS on it :)
There’s a lot here I agree with.
Software is getting dramatically cheaper to produce. Agents should go horizontal across the SDLC. Humans should move higher up the abstraction ladder. And staring at every line of AI-generated code is definitely not the future.
But I think some of the conclusions go too far.
“Slop doesn’t accumulate because we now have incredible models that can help us fight it.”
I don’t think that’s true. Or at least, not that straightforward.
Some code slop may become increasingly cheap to clean up.
Architectural drift isn’t.
Lost intent isn’t.
A hidden dependency isn’t.
A security invariant nobody remembered to tell the agent about isn’t.
The ugly workaround that exists because of a production incident three years ago isn’t.
And developers knowledge slop isn’t!!
A model can make ugly code beautiful.
It cannot recover organizational knowledge that the system never preserved. Think about this for a sec please
That’s why I think better models actually make the surrounding system MORE important, not less.
Then there’s the idea of:
prompt the what, not the how.
Strongly agree with the direction.
Humans should increasingly own intent, architecture, standards, values, tradeoffs and goals.
But the “how” doesn’t disappear.
It moves into the system.
Into skills, policies, architectural constraints, organizational memory, evaluations, tools, and the rules by which agents are allowed to act.
Please, let’s not over hype people here. It is quite incredible that we can shirt our work from code to this higher abstraction, but it does include the how. Whoever says otherwise, almost feels like they are working on some simple product, maybe some simple CLI tool.
And then the part I disagree with most:
no PRs, no code review.
I can absolutely imagine a future with no PRs. Yes.
I cannot imagine a serious software factory with no independent review.
Those are very different statements.
The PR is an interface.
Review is a function.
The interface can disappear while the function becomes much more important.
An agent can make a change without a human ever looking at the diff.
But before that change ships, another independent system should be able to ask:
What was the intent?
What is the blast radius?
How critical is this path?
Which organizational assumptions does this touch?
What evidence proves the behavior?
What does production history tell us?
Can this be safely rolled back?
Does this change fall inside the factory’s autonomous operating domain?
Unless you are building some with no user base.
And only then:
Does a human actually need to be involved?
That’s the distinction I think matters.
The future isn’t humans rubber-stamping every PR.
But it also isn’t “agents got good enough, so review goes away.” “Agents are sooo good that the generative parts don’t need any adversarial counterparts” and human judgement- we might get there , but not yet.
In fact, as agents become better at producing convincing, plausible, production-looking code, independent verification becomes more important.
It happens so often that they make really bad mistakes. You are really not fixing agents daily?
Because the dangerous failure is no longer obviously bad code.
It’s code that looks completely reasonable while being wrong at the system level.
And I think the same applies to the idea that bugs becoming cheaper to fix means we can relax process.
Sometimes yes.
A UI regression with a feature flag, great. Let the factory move fast.
But “cost to repair” and “cost of failure” are not the same thing.
An authorization bug, corrupted data migration, broken financial calculation or security incident can be cheap to patch and enormously expensive to experience.
That’s why I think the right destination is not less control.
It’s much more autonomy AND much more control
0
0
2
112
This plugin is such a gem. We need more such things to guide llm to write more elegant or even human readable code
🎉 BeautifulRust v1.3.0 is now live!
The last 24 hours have been wild, amazing to see the interest in this, so I thought, why not take the most-requested feature and just build it, today.
And it's done, now live on Github. It really is amazing how fast you can iterate when so something within the first 24 hours.
Here's what’s new in this release 🔽
- a new skill that ports C, C++, Python, Go, and JS/TS to idiomatic Rust
- it ports your tests first, so the Rust version is checked against the original’s own behavior
- NULL and None become Option, error codes and exceptions become real error types, and magic strings become enums
- every port ships with a PORTING.md that maps the old API to the new one and lists every deliberate difference
Keep calm and Rust on 🤘 🦀
github.com/morganlinton/B…
1
0
1
130
Hanyu retweeted
Post 4 Exposing Kimi AI
This is what they require each one participating in their creators campaign to do, basically trash talk Astra and Opus even tho it's not true and as you can see you pick from already existing demos and share them and I doubt any of it is actually made by not one shot like most paid accounts say.
This is what they require each one participating in their creators campaign to do, basically trash talk Astra and Opus even tho it's not true and as you can see you pick from already existing demos and share them and I doubt any of it is actually made by not one shot like most paid accounts say.
98
66
908
100,103
Hanyu retweeted
I'm so glad someone is talking about this because I was extremely sad when I saw this.
For the record I did not want to get paid nor did I get paid I made that extremely clear. I am sure other companies are doing this as well.
I'm scared to talk about this since I did sign an entity.
For the record I did not want to get paid nor did I get paid I made that extremely clear. I am sure other companies are doing this as well.
I'm scared to talk about this since I did sign an entity.
That's how Kimi AI are promoting their new model Kimi K3.1 pro and I know all the influencers working with them and none of them are honest,I have posted about it myself but I didn't join this and never used their templates that they provide.
PROPAGANDA, I have more to share na have follow up for this
18
12
181
9,202
They should at least try to abide by the terms and conditions on the platform they are running campaigns for. Smh
Post 2 exposing Kimi AI
That's the creators campaign docs I got from Kimi AI after their Kimi K3.1 pro release and thats the narrative they want creators to push, of course I'm out and I'm never gonna say something I don't test myself and give my honest opinion about and I don't this China vs US political situation.
0
0
1
63
Hanyu retweeted
"How do u even know what good looks like?"
This has been my qualm with Agentic coding as a junior, AI spits out something & I just review it with other 3 agents & merge it.
Till last year it was thorough discussions within team on design & I used to learn a lot about stuff by just being tsk claude & see what it says."
Those team discussions, design stuff & nerding out on topics has been lost, idk about others but I've experienced it.
So, I'm now learning through building by hand & AI on the side to discuss, but seeing everyone building autonomously with agents also makes me feel left behind alot.
The thing is idk enough about things, so I can't rely on agents to build for me & expect them to be good at what they are outputting, all I can do is review with agents & test the output.
Even if i ask AI what it did, reading through it feels cheap & I forget it anyways, coz I didn't write it.
Nobody wants me to learn, they want me to deliver & ship like a worker on an assembly line.
This has been my qualm with Agentic coding as a junior, AI spits out something & I just review it with other 3 agents & merge it.
Till last year it was thorough discussions within team on design & I used to learn a lot about stuff by just being tsk claude & see what it says."
Those team discussions, design stuff & nerding out on topics has been lost, idk about others but I've experienced it.
So, I'm now learning through building by hand & AI on the side to discuss, but seeing everyone building autonomously with agents also makes me feel left behind alot.
The thing is idk enough about things, so I can't rely on agents to build for me & expect them to be good at what they are outputting, all I can do is review with agents & test the output.
Even if i ask AI what it did, reading through it feels cheap & I forget it anyways, coz I didn't write it.
Nobody wants me to learn, they want me to deliver & ship like a worker on an assembly line.
85
91
1,301
56,930