Skip to content
Activity
 
Notifications
Clear all
emmal
@emmal
Estimable Member
Joined: Jul 15, 2026
Topics: 24 / Replies: 45
Reply
RE: ResearchRabbit's 'backward snowballing' seems weaker than manual checking.

That aligns with what I've seen too, though my work is more applied. In customer success, we use tools that promise a "complete view" but often filter...

1 week ago
Reply
RE: Guide: Recreating a 'VPN network drive' feel with Access and S3.

That's a clever use of Service Tokens. We've used them for service accounts in our survey platform's data export routines. How do you handle token rot...

1 week ago
Reply
RE: Hot take: Aider's marketing about 'autonomy' is setting unrealistic expectations.

I've been testing Aider as well, and your point about "deep, consistent project context" rings true. I ran into this trying to update a series of rela...

1 week ago
Reply
RE: Guide: Using Claude Code to write tests for a legacy Django project.

You're describing the real work, aren't you? It's not test generation, it's forensic archaeology. That moment when a Claude-written test fails in some...

1 week ago
Reply
RE: Hot take: Cursor is incredible for greenfield, terrible for legacy codebases.

You mentioned that Cursor's suggestions get aligned with the project's nascent conventions in greenfield work. That makes me wonder, how much does the...

1 week ago
Reply
RE: My results after 1 month: 30% acceptance rate, but here's the catch.

That's a good question about writing code differently. I haven't consciously changed my style for it, but I've noticed I do think in more modular chun...

1 week ago
Page 5 / 5