Thorsten Ball
Co-founder of Amp and co-host of the Raising an Agent podcast. Wrote Writing an Interpreter in Go.
Thorsten Ball did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter All topics · Newest first
-
Their wordsThis is not the time to try and land big enterprise contracts if that enterprise isn't willing to move as fast and you'll need to move to keep up with the changes.
- 5 days earlier
-
Their wordsA system that continuously flows is safer than a system that starts and stops in spurts.
- 1 day earlier
-
Their wordsBut all indications point towards price/intelligence dropping.
- 3 days earlier
-
Their wordsUse the latest and greatest models. Everything else is potentially a waste of time. If a model is wrong 10% of the time, you don't know which 10%, so you end up making multiple attempts.
-
Their wordsI'm not convinced it adds slop. And even if it does, I'm not convinced the result is unmaintainable.
-
Our reading
Tell a coding agent what you want rather than how to do it; you will often get better results.
Their wordsDescribe What you want, now How you'd do it. You'll often get better results.
-
Their wordsWhat stopped hallucinations? Tool calls. They let agents touch our reality. If the agent can't see something, it makes it up.
-
Their wordsSo let it run what it builds end to end, let it read production logs, deploy, watch the rollout, cut the release, flip the flag, triage the bug report and email the customer. Anything you can see, the agent should see too.
-
Their wordsKnowledge piles up in the codebase: AGENTS.md files, skills, scripts, docs. But do agents actually use it? Spawn five blind agents, control vs. treatment, and find out. Agents are really, really good at running experiments.
-
Their wordsEach agent should be able to install and run whatever it needs to get job done. Easy in remote machines, yucky in local dev.
-
Their wordsDon't iterate with the agent. Let it build tools to iterate. Not "let's try this. ... ah no, let's try that." Instead: "Generate 20 variations and a little page that lets me combine and test them."
-
Their wordsAsk for irrefutable proof. Biggest game changer. Agents are really good at producing proof: end-to-end walkthroughs, demo videos, before/after numbers.
-
Our reading
Don't wait for your agents; let them wait on you, with bigger, batched, asynchronous tasks.
Their wordsDon't wait for your agents. Let them wait on you. If you worry about TTFT, you're probably doing something wrong. Lean into async. Give them bigger tasks, be more ambitous. Batch instead of back and forth.
-
Their wordsAutomation/schedules/wake-up/heartbeat are killer feature. Didn't realize it, but missed it dearly once it was off.
-
Our reading
Stop managing an agent's context by hand: compaction works very well, so keep one thread per task.
Their wordsEvery thought you spend wondering about "is it using 300k or 380k tokens?" is wasted time. Compaction works incredibly well. Don't manage context by hand. One thread = one task.
-
Their wordsDon't let agents write for humans. Except: debugging steps, inicident reports, some docs. Mechanical stuff where human on other end doesn't matter that much.
-
Their wordsReview only code with high blast radius. There are <5 central files -- those I review. Database migrations, yes. Closure vs. class, a neater type, variable names, even duplication: I don't care anymore.
- 1 day earlier
-
Their wordsAI creates slop? Nah. It's actually the slop antidote. You just need to be willing to take it.
- 1 day earlier
-
Their wordsI know quite a few people working in industrial/manufacturing sector and they have a 6 months notice period. This will also never, ever change in Germany.
- 6 days earlier
-
Their wordsit's now much faster and easier to change code. Years ago a wrong decision could cause days and weeks of refactoring. Now? Probably less.
-
Their wordsYou can now have a team that ships fast, ships a lot, makes a ton of money, delights customers, builds a great product that's beloved AND no code reviews, no PRs, without yoloing to main.
- 1 day earlier
-
Their wordsWith agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
- 5 days earlier
-
Their wordsBut it's the wrong advice to not rethink everything right now.
-
Their wordsBut we don't know, because no one truly knows what will be important in the future.
- 3 days earlier
-
Their wordsall the fiddling with worktrees, with custom tab management, and notifications systems, and agent spawn wrappers is as productive as someone changing colorschemes in Vim eighteen times per day.
- 4 days earlier
-
Their wordsif an entity can write a 1000 line program without ANY mistake and any compile error -- do you really think it needs the exact same crutches we do?
- 1 day earlier
-
Their wordsI feel that the people who love stagnation got enough of what they wanted and I hope that we are at an inflexion point where we finally break free from the oppressive rule of stagnation.
-
Their wordsIf you believe that Rust isn't needed for agents anymore because they're good at mem alloc then you also have to believe aspects of testing become useless.
- 1 day earlier
-
Their wordsIf it works, if it's performant, if it has no bugs, if you understand how it works, if the agent can modify it a month from now, to your liking, is it slop?
- 1 day earlier
-
Their wordsBiggest source of confusion is that everyone - spent wildly different # of tokens in last 2 years - works in diff codebases - with diff languages - and diff requirements - in diff teams - with diff processes - in diff companies and then says "models are [good|bad]"