@currents_dev

Testing CI intelligence platform - troubleshooting, analytics and performance for humans and agents.

 Vancouver, BC, Canada
currents.dev
Joined June 2021
  • Tweets192
  • Following776
  • Followers203
55Media
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Replying to @iamdevloper
This is the way to go! 馃憦馃憦馃憦
27
Replying to @RyanEls4
You forgot the first rule: If it works, don't touch it!
6
Replying to @muchiriih @GithubProjects
@muchiriih @GithubProjects
1
18
currents.dev retweeted
currents.dev
@currents_devOct 23
Replying to @GithubProjects
Already did ;)
1
3
34
989
What can possibly go wrong?? 馃拝馃拝馃拝
3
36
Replying to @RyanEls4
Hurts extra this week!
17
Replying to @natmiletic
Pictorial representation of people not using AI to code.
4
242
Replying to @kapilansh_twt
Anyone refusing to use AI for code generation is living in a cave. Anyone saying that AI is perfect and you just need one prompt is delusional. What's needed is a system that enables the verification of what agents have done. With full history, context and the like.
24
Replying to @davidfowl
A new system is needed. - to verify that what agents built is in fact correct - to let agents know what broke so that they can correct - to have history and context Verification is the need of the hour.
79
Replying to @GithubProjects
Already did ;)
1
3
34
989
currents.dev retweeted
currents.dev
@currents_devOct 22
Replying to @theo
Only thing AI is missing is 'verifying' the output of what it has produced. e2e tests help but there needs to be a system around it. Call it verification engineering, proof-driven-development, reliability layer or something else. But there needs to be a system for that
1
1
140
Don't worry people, it's safe :)
2
58
Replying to @theo
Only thing AI is missing is 'verifying' the output of what it has produced. e2e tests help but there needs to be a system around it. Call it verification engineering, proof-driven-development, reliability layer or something else. But there needs to be a system for that
1
1
140
Replying to @ChShersh
To prevent this, you need some sort of evidence capture mechanism, that is searchable and can be handed off to an agent without consuming its full context window. Do that and you'll ship crazy fast!
1
35
Replying to @supabase
I delegated a task to Claude. Came back to see the results after an hour. Only to see that it had asked for a permission 57 minutes ago. 馃ゲ
1
65
Replying to @RyanEls4
the only correct way haha
1
2
33
currents.dev retweeted
currents.dev
@currents_devOct 21
Replying to @theo
Everyone will move to E2E tests. At the current volume of code generated by agents, verification is the new bottleneck. And you can't do that by code review given the volume of PRs. Plug in some E2E tests and a mechanism to capture and share evidence and you're good to go.
3
3
131
Replying to @theo
Everyone will move to E2E tests. At the current volume of code generated by agents, verification is the new bottleneck. And you can't do that by code review given the volume of PRs. Plug in some E2E tests and a mechanism to capture and share evidence and you're good to go.
3
3
131
Replying to @IamAroke
One other tip here is to sanitise your db on entry/exit. Saves a lot of headache later on.
1
2
35
Replying to @FlyaKiet
Curious to know the volume of code/PRs generated and how it holds up at high enough volume (a few thousand a week)
1
18
Load more