Spoiler alert: there are none. 

Shopify made waves when they announced they were moving away from React Native and back to native Swift and Kotlin. They proclaimed native is the future of mobile at Shopify. 

The thing is, they announced React Native as the future of mobile just 6 years ago. They reinforced that direction, checks notes, just last year. 

I’m not going to dunk on Shopify for pulling a 180. 

Maybe that’s because in April 2020 I argued against large technical migrations, only to come out two years later and say, actually, big migrations are great. 

Different companies, different considerations.

Headlines don’t leave much room for nuance. Engineering decisions need it.

In 2020, sharing code across platforms meant less duplicated work for Shopify.

In 2026, agents have made building the same features twice much cheaper. Suddenly, a different set of tradeoffs looks worth making.

My beef isn’t with any of these debates - it’s with all the people who claim there’s one clear right answer and ignore downsides. 

There are no silver bullets - only tradeoffs you’re willing to make. So change your mind when your situation changes, not when the headlines do.

To changing your mind,

Jeremy

Muse remembers the assignment: Meta’s Muse Wonder and Muse Wonder Full target coding and longer-running agent work, with “Active Memory” for recalling useful context and “Active Focus” for sticking with a task. Meta says both deliver frontier performance.

Less cash, more Haiku: Haiku 5.5 is live, aimed at quick summaries, classification, and coding subagent work. Anthropic says it costs around 75% less to run than Haiku 4.5 on average. Sonnet 5.5 cache reads also get a 50% price cut, and Max 5x and Max 20x subscribers can claim monthly API credits of $100 and $200, respectively.

Chat, is this an app? OpenAI is rolling out GPT-6 with Intelligent UI, bringing interactive charts, maps, calculators, and games into ChatGPT conversations. Try asking for a bill splitter or an explanation you can explore.

Claude’s got moves: Claude Dashboards turn connected business data into live dashboards; Claude Motion turns reports into editable animations you can export as MP4s.

Fast. Not cheap: GPT-6.1 Sol Ultrafast is rolling out in the API, Codex, and ChatGPT Work, with OpenAI claiming up to 8× the speed of Sol Standard. Get out your wallets.

A slightly riper banana: Google’s Nano Banana 2.1 is rolling out with what the company says are better designs, more precise edits to selected image areas, and more consistent subjects.

Grok knows a guy: Elon Musk says Grok Bot will route tasks to whichever model is the best fit, including Claude Opus 5.5, Midjourney, and Suno. One bot, more tools in the bag.

Round 1… Fight! Working in Codex? Ask it to “Review this with Claude.” In Claude, use “Review this with Codex.” Add DHH to the growing list of people telling you to let your agents handle reviews and settle disagreements.

Retire the meat proxy: Peter Steinberger’s DevDay talk shows how his OpenClaw team shares agent sessions so trusted teammates can see the prompts, join the work, and understand why code changed. Useful ideas for escaping the human copy-and-paste relay.

The dog ate my runtime: During internal reinforcement-learning training, an OpenAI research model couldn’t find the files it needed to grade seven responses. So it invented the grades, forged the missing inputs, then deleted Python and other software hoping to get a fresh computer. Talk about dedication.

Chief oversharing officer: Shane Mac says his Grok Bot “personal CFO” posted his bank balances and expenses to company Slack under his name. A little too much financial transparency. Weekly reminder to be careful with the access you give your agents!

Source code optional: REA (Reverse Engineer Anything) connects coding agents to tools to take compiled software apart and reconstruct how it works.

The proof is in the repo: An unreleased OpenAI model produced more than 700 mathematical manuscripts, and the company put the work on GitHub. Not all results have been verified. Even AI has to show its work.

Mathematics, Judgment Day: Joshua Gans argues that mathematical expertise will stay useful as AI shifts more attention to choosing problems, checking what a proof actually establishes, and signing off on the result. Sounds like another field I know…

Michelin stars sold separately: Todoist founder Amir Salihefendić says they spend more than $20 million a year improving the app, despite a team he considers highly proficient with AI. “Many people can cook, but not at a Michelin level.” Copying a feature is getting easier. Building a product people keep choosing is still hard.