Advertisement · 728 × 90

Posts by Ty Dunn

Video

Quality control for your software factory.

We just launched Continue on Product Hunt.

Source-controlled AI checks on every pull request.

Would love your support: www.producthunt.com/products/con...

1 month ago 2 1 0 0
Post image

this one goes out to the agents in the factories

1 month ago 1 0 0 0

30 tickets of product debt. 8 waves of parallel Claude Code sessions. Between waves, a trip to the post office. By the end: +283 net lines and a map of every moment that actually required a human.

1 month ago 0 0 1 0
Preview
283 Net Lines and a Passport I shipped 29 PRs, renewed my passport, and had two conversations that landed on opposite ends of the same question.

Yesterday I shipped 29 PRs, renewed my passport, and had two conversations that landed on opposite ends of the same question.

blog.continue.dev/283-net-line...

1 month ago 2 1 1 0
Preview
Increase font size on mobile by TyDunn · Pull Request #99 · continuedev/amplified.dev Summary Bumps base html font-size from 16px to 17px at the 768px tablet breakpoint Increases body text (.section p, .closing p) from 1.05rem to 1.1rem on tablet, and from 1rem to 1.05rem on mobile...

PR merged: github.com/continuedev/... ✅

appreciate the kind words!

1 month ago 1 0 0 0

11 checks for one HTML file. Each protects a decision easy to violate when agents open PRs. Writing them forced us to say what "good" means. Tests for your taste.

See the checks: github.com/continuedev/amplified.dev/tree/main/.continue/checks

Try it: continue.dev/walkthrough

1 month ago 1 0 0 0

"Resist Complexity": "The site is HTML, CSS, and images. That's the point. Don't add what you don't need."

No npm. No Tailwind. No React. CSS in a style tag. Not a problem to solve — a decision. The check enforces it every PR, especially from agents that love adding deps.

1 month ago 1 0 1 0
Advertisement

The site has two hidden features. Type "amplify" and the text lifts, lavender glows: "↑ the work moves up." There's also j/k navigation — zero UI. If you know, you know.

Each has its own check. Both share one rule: zero visual footprint.

1 month ago 1 0 1 0

"Accessibility as Care" — "The site should work for everyone — not just developers on MacBook Pros, but the people you love who don't have a framework for what's happening."

Reduced motion. Descriptive alt text. WCAG contrast. Each rule is a small act of noticing someone exists.

1 month ago 1 0 1 0

"No Product Creep" watches for the site drifting from essay toward marketing. Analytics scripts, newsletter signups, CTAs to commercial pages.

The site's power comes from what it is not. The moment it starts selling, it stops being the thing people share.

1 month ago 1 0 1 0

The essay has a six-section narrative arc. A check called "Editorial Voice & Narrative Arc" protects it.

Flags corporate language. Enforces second-person voice — peer to peer, not product to customer. Pull quotes must be turning points, not summaries. No linter can do this.

1 month ago 1 0 1 0
Preview
Developers amplified, not automated Every time a layer of the work became infrastructure, the role didn't shrink. AI is the next layer in it.

amplified.dev is a single-page essay arguing developers are amplified, not automated. One HTML file, inline CSS, vanilla JS. No frameworks.

We wrote 11 checks for it. Checks don't have to protect code — they can protect taste. Here's what ours look like.

1 month ago 7 3 2 2
Preview
From Vibe Engineering to Continuous AI Vibe coding emerged earlier this year to describe fast, loose experimentation with AI. Now, Simon Willison has proposed "vibe engineering": Vibe coding is irresponsibly building software through dic...

Read more on the Continue Blog: blog.continue.dev/from-vibe-en...

6 months ago 0 0 0 0
Post image

Continuous AI isn't about removing developers—it's about working at the right abstraction level.

Sometimes that's hands-on vibe coding

Sometimes careful vibe engineering

Increasingly, it's orchestrating remote agents while staying accountable for what ships

6 months ago 1 0 1 0
Post image Post image

The shift happens when you trust an agent to run 5+ minutes unsupervised. You get bored waiting, so you spin up a second agent. Then three. Four. Five.

Suddenly your whole team is doing this and you need: secure execution, event-driven triggers, overnight runs, monitoring, etc.

6 months ago 0 0 1 0
Advertisement

We are evolving from vibe coding → vibe engineering → Continuous AI

- Vibe coding = fast AI experimentation
- Vibe engineering = sophisticated AI-assisted production development as individuals
- Continuous AI = orchestrating agents across your entire dev lifecycle as a team

6 months ago 2 1 1 0

So 🔥
I love when startups do research and just ship in product. Skip the benchmarking theatre.

7 months ago 5 2 0 1
Video

Introducing Instinct 🐺, a new state-of-the-art open Next Edit model trained by @continue.dev

Runnable with @ollamabot.bsky.social and available today in VS Code

7 months ago 17 5 1 2
Preview
Context Engineering: The Bottleneck to Better Continuous AI Back in 2019, I gave a presentation about building contextual AI assistants at the O'Reilly AI Conference. While AI has progressed dramatically since then, one challenge has remained constant: the art...

blog.continue.dev/context-engi...

9 months ago 1 0 0 0
Post image

There is so much room for context engineering improvements at large organizations

9 months ago 5 1 1 0
Post image

“Developers will be the ones who drive how many languages we have. Their actions and their stewardship of their niche programming languages will determine whether we have more or less”

- @ty.energy in 'The programming languages facing an AI-driven existential crisis' by @karimcmack.bsky.social

10 months ago 3 1 1 0
Post image

@continue.dev is hosting the AI Native Dev - SF Meetup at GitHub HQ (thanks to Kevin Crosby!) with @jedi.be and friends ️‍🔥

10 months ago 3 1 1 0
Post image

It's hard to tell from your screenshot, but it looks like it didn't use your MCP server. You need to be in Agent mode, and the MCP needs to be connected, which you can verify in the notch. Then you should see the tool from the MCP being used 👍

11 months ago 0 0 0 0
The Open Source AI Code Assistant That Puts You in Control (with Continue CEO Ty)
The Open Source AI Code Assistant That Puts You in Control (with Continue CEO Ty) YouTube video by DevAI - Hosted by Balaji Siva

@ty.energy joined Balaji Sivasubramanian on the DevAI podcast to discuss the open architecture that we believe will underlie the future of AI-native software development 😎

www.youtube.com/watch?v=FwZq...

1 year ago 3 1 0 0
Advertisement
Post image

Read the entire discussion: news.ycombinator.com/item?id=4349...

1 year ago 1 0 0 0
Post image

We launched on Hacker News yesterday! There was a great discussion on custom AI code assistants. In case you, missed it:

1 year ago 5 2 1 0
Preview
Continue wants to help developers create and share custom AI coding assistants | TechCrunch Continue helps developers create customized, contextual coding assistants that can connect with any model and development environment.

It’s critical that an open architecture underlies the future of AI-enhanced software development. This is why we are launching Continue 1.0 with hub.continue.dev today: techcrunch.com/2025/02/26/c...

1 year ago 5 3 0 0

@continue.dev 👋

1 year ago 2 0 0 0

I am now @ty.energy 👋

1 year ago 2 0 0 0
Preview
Recursive Worlds | Antikythera Recursive Worlds is a lecture by Sara Imari Walker recorded in July 2024 in London as part of Antikythera’s Cognitive Infrastructures Studio lecture series.

Lineages of information structuring matter have led me to this Recursive Worlds lecture by Sara Imari Walker (and Bluesky, hello world!)

antikythera.org/films/recurs...

1 year ago 3 0 0 0