Opus 4.5 changed everything (Interview)
Episode
104 min
Read time
4 min
Topics
Fundraising & VC, Artificial Intelligence, Software Development
AI-Generated Summary
Key Takeaways
- ✓Agentic Model Quality Threshold: Sonnet 3.5 could build agentically but produced sloppy, spaghetti code that stalled on errors neither the developer nor the model could debug — because the developer hadn't written the code themselves. Opus 4.5 crossed a threshold where it one-shots functional native Windows tools using correct WinUI libraries, produces well-structured readable code, and completes full working apps in an afternoon. The practical test: Burke built a screen-capture-to-GIF tool, then extended it into a full screen recording editor in a few hours.
- ✓Personal Software Economics — The SaaS Killer Pattern: When a model reaches sufficient capability, replacing paid SaaS subscriptions with custom-built personal software becomes viable in a single afternoon. Burke replaced a paid routing app his wife used for her yard-sign business. Adam replaced an $500–$800/year invoicing service by prompting Claude Opus 4.6 with extended thinking to generate an optimal prompt, then handing that prompt to Augment Code's Auggie CLI overnight — waking to a working Rails app with invoicing, PDF generation, and email built in.
- ✓Subsidized Token Economics Won't Last: GitHub Copilot at $40/month offers request-based billing where one agent run doing 6,000 operations counts as a single request, with 1,500 requests per month included. Claude's $200/month max plan supports roughly one billion tokens monthly at an estimated provider cost of $25,000 — a $24,800 subsidy per user. Burke explicitly states this pricing cannot persist indefinitely and developers should maximize usage now, treating the current window as a finite opportunity before costs normalize.
- ✓Plan Mode as Context Extraction, Not Documentation: The value of agent plan mode is not producing a written plan — it is forcing the model to surface all the requirements and constraints the developer forgot to specify in the initial prompt. Running four to six planning loops with Opus 4.6 before execution dramatically improves output quality. Burke's current workflow: plan mode in Copilot CLI
What It Covers
Adam Stacoviak of The Changelog interviews Burke Holland from GitHub Copilot about how Claude Opus 4.5, released around December 2024, created a measurable step-function improvement in agentic coding capability. The conversation covers practical AI-assisted development workflows, the economics of subsidized model access, the future of software craftsmanship, and whether developers will be replaced or transformed into polymaths.
Key Questions Answered
- •Agentic Model Quality Threshold: Sonnet 3.5 could build agentically but produced sloppy, spaghetti code that stalled on errors neither the developer nor the model could debug — because the developer hadn't written the code themselves. Opus 4.5 crossed a threshold where it one-shots functional native Windows tools using correct WinUI libraries, produces well-structured readable code, and completes full working apps in an afternoon. The practical test: Burke built a screen-capture-to-GIF tool, then extended it into a full screen recording editor in a few hours.
- •Personal Software Economics — The SaaS Killer Pattern: When a model reaches sufficient capability, replacing paid SaaS subscriptions with custom-built personal software becomes viable in a single afternoon. Burke replaced a paid routing app his wife used for her yard-sign business. Adam replaced an $500–$800/year invoicing service by prompting Claude Opus 4.6 with extended thinking to generate an optimal prompt, then handing that prompt to Augment Code's Auggie CLI overnight — waking to a working Rails app with invoicing, PDF generation, and email built in.
- •Subsidized Token Economics Won't Last: GitHub Copilot at $40/month offers request-based billing where one agent run doing 6,000 operations counts as a single request, with 1,500 requests per month included. Claude's $200/month max plan supports roughly one billion tokens monthly at an estimated provider cost of $25,000 — a $24,800 subsidy per user. Burke explicitly states this pricing cannot persist indefinitely and developers should maximize usage now, treating the current window as a finite opportunity before costs normalize.
- •Plan Mode as Context Extraction, Not Documentation: The value of agent plan mode is not producing a written plan — it is forcing the model to surface all the requirements and constraints the developer forgot to specify in the initial prompt. Running four to six planning loops with Opus 4.6 before execution dramatically improves output quality. Burke's current workflow: plan mode in Copilot CLI
Notable Moment
Burke describes letting a GitHub Copilot CLI agent run continuously in a loop for days, autonomously deciding which features to add to a multiplayer game where users roleplay as baby birds. He acknowledges it will likely produce an unwieldy, unshippable result — and frames this as an honest illustration of exactly where autonomous agentic software development currently breaks down at scale.
Episode Transcript
Well, friends, the end is here. Not the end of the show, but the end of a fantastic partnership. I started the change law back in 2009 with Benevolent, and the show has been a beloved breakout ever since. In 2012, Wynn stepped away to lead GitHub's API. So I had to reinvent what the change all was. That same year, Jared joined as a contributor and guest on the podcast. Eventually, it made sense for him to join as a full time host with me. I grew into a business partnership where Jared joined as a part in the business and managing editor, and the rest is kind of history. Without going into too much detail, late last year, it made the most sense to part ways. No drama, no issues. We remain friends. Just time for change. And this week is the week of that change. Today, I am solo once again on this podcast, and of course, I'm reinventing what it is we do here. For now, it'll be more of the same. But in the near future, expect change, good change. In the meantime, you can join the community at changelaw.com/community. It is free to join. Hang with us in Zulu chat. It's a ton of fun and to my dear friend Jared, you will be missed. Thank you so much for the many laughs and all the good times and just everything. Friends forever. Alright. Let's do the show. Welcome back. This is the changelog. I'm Adam Stokowiak, editor in chief here at changelog.com. And today, I'm joined by Burke Holland from the GitHub Copilot team, and we're talking about how opus four point five changed everything. This is coming straight from a post Burke shared in January, just after the AI holiday high, we were all on from the generous two X usage bump with Claude and the major step function Opus 4.5 offered. Burke and I get into all the details. Opus 4.5 may have started the fire, but GPT 5.3 codex is certainly living up to the hype. A massive thank you to our friends and our partners over at fly.io. That is the home of changelaw.com. Learn more at fly.io. Alright. Let's do this. Well, friends, I'm here with my good friend, Chris Kelly, over at Augment Code. Chris, I'm a fan. I use Augie on the daily. It's one of my daily drivers. I use Cloud Code. I use Augment Auggie, and I also use AMP code and others. But Auggie, I keep going back to it, and here's where I'm at. I feel like not enough of our audience knows about Augment code, not enough about Auggie, the CLI. It's amazing. I love it. What can you share? Yeah. We often say Augment is the best coding assistant you've never heard of. And that's both frustrating as someone that works there and is, like, very proud of the work we've done, but also, like, inspiring. Like, we wanna go …
Get the full transcript (19,453 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 101-minute episode.
Get The Changelog summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
by OpenAI
“Burke's Anvil agent classifies tasks as easy, medium, or hard, then delegates design work to Gemini, code refactoring to GPT-5.3 Codex, and planning/communication to Claude Opus 4.6.”
by Google
“Burke's Anvil agent classifies tasks as easy, medium, or hard, then delegates design work to Gemini, code refactoring to GPT-5.3 Codex, and planning/communication to Claude Opus 4.6.”
- Claude Opus 4.5Recommended
by Anthropic
“Claude Opus 4.5, released around December 2024, created a measurable step-function improvement in agentic coding capability.”
- GitHub CopilotRecommended
by GitHub
“GitHub Copilot at $40/month offers request-based billing where one agent run doing 6,000 operations counts as a single request, with 1,500 requests per month included.”
- AnvilRecommended
“Burke's current workflow: plan mode in Copilot CLI → autopilot with a custom agent called Anvil → confidence-threshold loop.”
- Augment Code Auggie CLIRecommended
by Augment Code
“Adam replaced an $500–$800/year invoicing service by prompting Claude Opus 4.6 with extended thinking to generate an optimal prompt, then handing that prompt to Augment Code's Auggie CLI overnight — waking to a working Rails app with invoicing, PDF generation, and email built in.”
by Microsoft
“Teams like VS Code's engineering group are actively building AI-assisted workflows specifically for production-quality software.”
- Claude Opus 4.6Recommended
by Anthropic
“Adam replaced an $500–$800/year invoicing service by prompting Claude Opus 4.6 with extended thinking to generate an optimal prompt.”
company
“Sponsors: Squarespace”
- Augment CodeRecommended
“Adam replaced an $500–$800/year invoicing service by prompting Claude Opus 4.6 with extended thinking to generate an optimal prompt, then handing that prompt to Augment Code's Auggie CLI overnight.”
“Sponsors: Fly.io”
“Sponsors: Notion”
More from The Changelog
We summarize every new episode. Want them in your inbox?
Forking Cal.com to closed source (Interview)
Postgres at PlanetScale (Interview)
Canary tokens and digital tripwires (Interview)
From open source hits to OpenAI (Interview)
MCP on Code Mode (Interview)
Similar Episodes
Related episodes from other podcasts
Odd Lots
Jul 6
These Are the Sharps Actually Making Money on Prediction Markets
Latent Space
Jun 2
GitHub's plan for Agents — Kyle Daigle, GitHub
The AI Breakdown
Apr 28
The AI Subsidy Era is Over
Startups For the Rest of Us
Mar 24
Episode 825 | Talking Tailwind CSS and Founder Fitness (with Adam Wathan)
WorkLife with Adam Grant
Mar 17
ReThinking: Breaking leadership barriers with hockey coach Jessica Campbell
Explore Related Topics
This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into The Changelog.
Every Monday, we deliver AI summaries of the latest episodes from The Changelog and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime