Louie Bacaj

Engineer turned Entrepreneur, turned Engineer, and the cycle continues.

[Louie Bacaj @LBacaj]

I think the best way to do code reviews now is to do:

1) Will it break anything else reviews

2) Will it actually work reviews

And in priority order. Anything else is futile, if you want to keep up with the onslaught of PRs.

[kache @yacineMTB]

At my company we stopped doing code reviews. There's no point now

[Louie Bacaj @LBacaj]

@janaka_a @trq212 @zainfathoni Ah! See, now that makes more sense :)

Not if you’re paying the enterprise fees for tokens though.

[Louie Bacaj @LBacaj]

@LanceTreyark True.

But at least claude has the courage to take responsibility :)

[Louie Bacaj @LBacaj]

Claude after it wipes out your entire prod DB, and the backups

[Insider Wire @InsiderWire]

#BREAKING: Anthropic’s AI coding agent ‘Claude’ reportedly wiped a company’s production database and backups in 9 seconds.

[Louie Bacaj @LBacaj]

They’re saying AI will replace me. But tbh I can’t wait for it to replace me so I can sit back on a beach somewhere.

But so far all it’s done is make me work harder. And it feels like there is an infinite amount of ideas to explore. Claude give me a day off please.

[Louie Bacaj @LBacaj]

@EthanHe_42 Prompt is cheap, show me the talk that led to it.

[Louie Bacaj @LBacaj]

Everything is context now.

That one random chat we had about how we might build that thing, that’s context for our agents now.

[anton @abacaj]

“Make the models cheap to use”
“Great, they all forgot how to code”
“Now 10x the price”

[Louie Bacaj @LBacaj]

I think the reason this went so viral is because it’s a conflict of interest.

They give you the slop, then they charge you a lot for the slop fixer.

Yes, engineers reviewed code too but at least humans are incentivized not to waste time. Now claude incentivized to burn tokens.

[Claude @claudeai]

Introducing Code Review, a new feature for Claude Code.

When a PR opens, Claude dispatches a team of agents to hunt for bugs.

[Louie Bacaj @LBacaj]

@VicVijayakumar 💯

[Louie Bacaj @LBacaj]

@steipete @levelsio You just know they are doing some post release “optimizations” and they refuse to say they “nerfed it”

[Louie Bacaj @LBacaj]

@GergelyOrosz Everything has tradeoffs, no real free lunch in tech.

But imo, trading off some uptime for speed is an advantage for them given how fiercely competitive things are. Not many can do it well.

Compared to open ai they’re the underdog. To get a crazy outcome gotta do crazy things

[Louie Bacaj @LBacaj]

The equivalent of the industrial revolution for software engineering is upon us.

With all these AI agents, we’re no longer workers, we’re now factory owners.

But Factories perform best when we can conform things enough to fit their molds.

[Louie Bacaj @LBacaj]

@GergelyOrosz I love claude code, but thank God anthropic has competition… and we can move off if we need to.

[Louie Bacaj @LBacaj]

@fryry__ 💯

[Louie Bacaj @LBacaj]

Almost any software that does not work well with AI agents, is not going to make it.

I’m using a lot of tools with tons of UI, all of it will either have to be rewritten to be agent friendly, or it’s dead. For a lot of it too, slapping some MCP on it won’t be enough either.

[Louie Bacaj @LBacaj]

And a lot of ppl may not want to hear this but that old rule “the best UI/UX is no UI” is true for a reason.

And it’s clear to me now, agents are going to wreck through UI heavy tools