
Dan Adler
@DanielNealAdler
Followers
441
Following
7K
Media
21
Statuses
322
Ops/finance/data and a lot of coding @sourcegraph @ampcode. #T1D.
East bay, CA
Joined November 2011
It's just better.
I’m not one for AI hype but @AmpCode is the real deal. Tried it today after listening to @thorstenball on the Changelog podcast and it is hard to describe how good it is. I’ve never been this excited to build.
0
0
1
A pretty big moment. The first time my conversations really, ACTUALLY feel better from having multiple LLMs involved. @ampcode just lets them do what they do best.
0
0
13
All we think about is how to make @AmpCode the very best
All we think about is how to make Amp the very best. Not the best that fits into $__/month, not the best that uses only models from a particular model provider, but the very best.
0
0
4
RT @Will479242: Fun fact: I found out my account had a bug preventing me from getting FREE credits. The Amp team fixed it within 30 mins o….
0
2
0
@AmpCode threads are how I’ve gotten better. Legitimately the best way to learn is just reading other people’s transcripts.
0
1
6
Love how transparent @sqs @thorstenball are about their process of learning to use AI. This didn’t exist a few years ago! It’s okay to be a newb! We’re all learning.
Fascinating to look back at my first Amp threads and see how my own usage has changed 1,221 threads (and a few months) later. - Longer, more detailed initial messages, shorter followups.- Better context/prompts in my initial msgs to eliminate ambiguity/avoid pitfalls
1
1
11
Every dev tools sales rep and founder knows this argument well!. But as a user, there's just never been anything that so obviously pays back multiples as this gen of @AmpCode @claude_code etc., right? How can these cost so little.
WILD people think I'm spending "so much" on AI eng tools, when this is my YTD eng spend on @chatprd:. - claude $91.- @v0 $120.- @cursor_ai $335.- @ChatGPTapp $1500.- @DevinAI $2500.- @zapier $3621.- human engineers $100k. Dumb not to make that 100k as efficient as possible.
1
1
8
RT @sqs: All we think about is how to make Amp the very best. Not the best that fits into $__/month, not the best that uses only models fro….
0
1
0
I keep hearing "shipping fast is the only moat". But having taste is SO much rarer.
In 1st- and 2nd-gen AI coding tools you now see a proliferation of modes, toggles, and buttons. This feels off. AI UX done well should mean we don't have to point/click or get lost in a sea of rules or modalities. Sure, you may still have to type or articulate your intent, but
0
2
19
RT @sqs: I can't promise that Amp is right for every company today, but I can commit with everything I have that if you get Amp, it will st….
0
2
0
RT @jordanjhamel: the institutional knowledge around codesearch, Cody, etc has lead to @AmpCode pulling way ahead.
0
3
0
RT @sqs: Congratulations to Anthropic on Claude 4! We’ve been using Amp with Claude 4 internally for weeks. Amp is built for where the mode….
0
10
0
RT @thorstenball: Wrote down how Amp changed programming for me. Yes, I barely type code by hand anymore.
0
41
0
Here it is, a first look at Amp. From a session in which @Beyang and @thorstenball use Amp to work on Amp itself. Raw and uncut, including all Ahhs, Ohhs, and Oofs.
0
0
0