Amp is the coding agent and development environment that runs anywhere and everywhere.
amp-devs@ampcode.com
- Tweets 337
- Following 64
- Followers 26,552
- Likes 1,130
"Just use a cheaper model" sounds like saving money.
But fiber didn't just make your internet faster. It made whole new businesses possible. @thorstenball and @sqs discuss how the same is true with frontier models.
Would you prefer to save money with dial-up when your competitors are using fiber?
Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.
00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?
1
5
39
12,890
Would you prefer to save money with dial-up when your competitors are using fiber?
Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.
00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?
6
6
53
40,381
You can also watch it on YouTube: piped.video/3v7dIHh15dk
Or listen to it on Spotify: open.spotify.com/show/1AL44J…
If you want to listen to all of them: ampcode.com/podcast
3
1,374
Amp retweeted
I'm in Sydney this week, along with half of the Amp team.
Come hang out with us on Thu. Will ship your bugfixes and (good) feature ideas to main on the spot.
luma.com/9layr5ts
19
4
114
56,206
Amp retweeted
Amp is now free to use when you bring your own compute and model subscriptions/keys.
No more limits or fees for BYOK.
ampcode.com/news/free-agent
179
141
1,575
1,046,596
"I'm just pointing at things and saying, make it like this and ship this and do this. The altitude is so high. It's wild. Even compared to two months ago."
@thorstenball on using agents for the whole lifecycle of a feature: building, testing, shipping, monitoring the rollout, toggling feature flags, talking to users.
What is the computer for now?
In Raising an Agent S2E4, @sqs and @thorstenball explore how agents can do more than just ship code, discuss recent outages, and ask what happens to our computers when more work moves into Orbs.
00:00 Intro: What is the computer for now?
01:32 New models & aiming higher with agents
04:42 An agent's job after the code ships
10:19 Mini evals & keeping the team's context in threads
13:38 Performance testing & production canaries
18:36 Amp's recent outages & what went wrong
24:44 Shipping faster & the tradeoffs of redundancy
28:34 How fast can an engineering team go?
32:27 Making production logs & metrics useful to agents
37:15 Beyond local development
41:30 Agents building 3D models & virtual worlds
43:35 Simpler devices & dictating work on the go
47:29 What happens to the tools we love?
49:27 Steering, queuing & changing workflows
7
4
42
37,669
What is the computer for now?
In Raising an Agent S2E4, @sqs and @thorstenball explore how agents can do more than just ship code, discuss recent outages, and ask what happens to our computers when more work moves into Orbs.
00:00 Intro: What is the computer for now?
01:32 New models & aiming higher with agents
04:42 An agent's job after the code ships
10:19 Mini evals & keeping the team's context in threads
13:38 Performance testing & production canaries
18:36 Amp's recent outages & what went wrong
24:44 Shipping faster & the tradeoffs of redundancy
28:34 How fast can an engineering team go?
32:27 Making production logs & metrics useful to agents
37:15 Beyond local development
41:30 Agents building 3D models & virtual worlds
43:35 Simpler devices & dictating work on the go
47:29 What happens to the tools we love?
49:27 Steering, queuing & changing workflows
6
7
64
141,262
You can also watch it on YouTube: piped.video/7pstrDQ4xLs
Or listen to it on Spotify: open.spotify.com/show/1AL44J…
If you want to listen to all of them: ampcode.com/podcast
2
3,490
Amp retweeted
Queueing your messages to the agent made sense for easily distractible models.
Now? Amp sends your message to the agent without waiting.
It's way faster and more natural. Plus, more information makes the agent do better.
ampcode.com/news/steer-dont-…
11
7
110
58,300
"I could just replace that with EC2 and some shell scripts and get the same thing."
But could you?
Thoughts and question of when to build and when to buy.
And @sqs putting @thorstenball fully on the spot by asking him whether people should build their own Amp or not.
4
5
35
7,447
Amp retweeted
Amp now has GPT-6 Astra. It's very good and uses your linked ChatGPT sub.
Amp's `high` mode is gpt-6-astra medium (not xhigh, why in thread). In other Amp modes soon.
BTW: customize your Amp dial at ampcode.com/settings/dial or pick any GPT-6 Astra effort level in Raw Models
34
20
222
365,731
Amp retweeted
Your orbs now have their own high-res interactive Linux desktop.
Good for native app dev. Next up: computer use, but on orbs.
ampcode.com/news/desktop
18
14
189
127,017
Quinn on everyone now building developer tooling:
"Just building software to do X is only valuable if you can get people to pay and I think that's going to be a lot harder."
Raising an Agent, S2E3: When Tokens Flow Like Electricity.
@sqs and @thorstenball on what happens when intelligence gets cheap: build vs. buy flips, why everyone building software to build software to do X is probably incorrect, and when software starts to feel like owning a house instead of renting one.
00:00 Intro: Cheap intelligence & doing X instead of building software to do X
01:06 Back home after Munich & what's changed in how we build
02:06 Predictions: the price of intelligence drops, tokens flow like electricity
05:54 Everyone is building dev tools & why that's the wrong bet
06:57 Pet theory: engineers can't believe it's this easy
10:33 Orbs vs. EC2, a VPN & tmux
17:18 Build vs. buy when the models keep changing
20:14 If Amp is worth buying, why isn't an issue tracker?
27:34 Killing features & vibe coding the 2% of a SaaS product you need
30:03 Build on a solid core: glue code is the worst part
33:19 The two Amps: jellyware, homeowners & renters
37:01 Exporting the Amp way to more teams
43:42 Opinionated software from people you trust
6
1
44
407,218
Amp's ultra mode now uses Fable 5.1
Some notable improvements compared to Fable 5: better steerability, better at writing, and 35% cheaper per thread.
Read the full post with our observations and recommendations here: ampcode.com/news/fable-5.1
3
4
55
8,541
We're investigating an infrastructure failure that causes large parts of ampcode.com being unavailable.
Sorry about that. We'll keep you updated on ampcodestatus.com/.
15
2
92
10,219
What can United Airlines teach Anthropic and OpenAI about pricing?
Or, what does flying economy have to do with token subsidies?
Raising an Agent, S2E3: When Tokens Flow Like Electricity.
@sqs and @thorstenball on what happens when intelligence gets cheap: build vs. buy flips, why everyone building software to build software to do X is probably incorrect, and when software starts to feel like owning a house instead of renting one.
00:00 Intro: Cheap intelligence & doing X instead of building software to do X
01:06 Back home after Munich & what's changed in how we build
02:06 Predictions: the price of intelligence drops, tokens flow like electricity
05:54 Everyone is building dev tools & why that's the wrong bet
06:57 Pet theory: engineers can't believe it's this easy
10:33 Orbs vs. EC2, a VPN & tmux
17:18 Build vs. buy when the models keep changing
20:14 If Amp is worth buying, why isn't an issue tracker?
27:34 Killing features & vibe coding the 2% of a SaaS product you need
30:03 Build on a solid core: glue code is the worst part
33:19 The two Amps: jellyware, homeowners & renters
37:01 Exporting the Amp way to more teams
43:42 Opinionated software from people you trust
3
2
20
31,387