Codistry

* Don't learn to code. Learn to build! *
AI-first software development, on solid foundations.
Training, jobs, news, discussions and more.

[Codistry @codistryai]

Super proud to launch our weekly AI newsletter.

Keep up with the latest and most important news.

Quick read. No BS.

Subscribe free at
https://t.co/HI0DKcbS5r

[Boris Cherny @bcherny]

Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat code issues, building up a suite of e2e tests so they don't need to smoke test the app manually. These kinds of things were the highest leverage activities an engineer could do, because it multiplied their own output, which in turn meant they could build more things.

I think many of these automations have become even more important now. This is true for a number of reasons.

First, infra and DevX automation speeds you up. And if you are running an army of agents, each of those agents will be sped up also. More automation == more output per unit of time.

Second, moving things to code improves efficiency. Your agent could fix an issue every time it sees that issue happen, but that uses tokens and might miss cases. If Claude instead writes a lint rule, CI step, or routine, that class of issue can be fully automated forever. This is really what people are talking about when they talk about loops -- it's about automating entire types of busywork rather than solving them one off. This isn't a new idea at all. Engineers have been doing this for a long time!

Third and most importantly, automation makes it possible for others to contribute to the codebase more easily. Increasingly what I am seeing is engineers are contributing to codebases on day one because Claude can navigate the codebase for them, and that non-engineers are able to contribute to a codebase as effectively as engineers can. What gets in the way of both of these is domain knowledge that lives in peoples' heads rather than in automation -- the stuff you used to have to learn when ramping up. What has changed thanks to agents is the domain knowledge that can be encoded as infrastructure is no longer limited to what is expressible in lint rules and types and tests; it can now capture nearly all domain knowledge, encoded as code comments and skills and CLAUDE.md rules and memories. If I put up a PR for an iOS codebase I don't know and a code reviewer rejects it because it doesn't use the right framework, or if a designer builds a new feature and it gets rejected because it doesn't follow the right architectural patterns, these are failures of automation.

Every team should be writing the CLAUDE.md's, REVIEW.md's, skills, and docs that enable agents to productively work in their codebase with zero additional context from the prompter. This sounds crazy, and at the same time is a natural extension of the stuff engineers have always done: automate, and encode domain knowledge as infrastructure. As the model gets smarter and as the harness matures, this task becomes easier. In the meantime, it is on every team to look for ways to convert their domain knowledge to infra so that Claude can write code better, so that code review catches issues automatically, and so the next person working on your codebase can contribute more easily.

[Codistry @codistryai]

Vibe coding is fun and easy...

Until you're trying to figure out why your app broke. 😰

Building software that scales, stays secure, and survives real users is the hard part.

We show you how to build products, not just prototypes.

[Codistry @codistryai]

Seems like Fable isn't what it used to be :-( Disappointing!

[Codistry @codistryai]

Fable! We've missed you!

[Anthropic @AnthropicAI]

Claude Fable 5 will be available again globally tomorrow.

After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests.

We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort.

Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research.

Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again.

Read our full blog: https://t.co/VHyum831ri

[Codistry @codistryai]

Vibecoders:

What are you building?

Our founder build an app that supported 100 million monthly users.

As us anything.

[Codistry @codistryai]

This what Codistry is all about.

[Codistry @codistryai]

Most AI courses teach prompts.

We teach product building.

**Learn from a venture-backed CTO who scaled a platform to 100M+ monthly users.

Leverage AI to build, ship, and own scalable products.

18 seats left. Fully online. Starts Aug 17th.

Comment APPLY for the application.

[Codistry @codistryai]

If you can think through a problem logically and communicate it clearly, you can build software in 2026.

No coding experience necessary.

See how we're helping builders internationally: https://t.co/pUM1UQo9NK

[Codistry @codistryai]

Time and money.

They're the two things everybody wants more of.

So it's safe to say anything that makes you spend a lot of both is not optimal.

For product developers, there used to be no other choice...

[Codistry @codistryai]

What HASN'T changed?

The need to clearly design what you're building.

-How data moves through a system.
-What happens when something breaks. (And why it broke in the first place.)
-How to take a problem and translate it into a set of instructions on which a machine can execute.

[Codistry @codistryai]

AI-assisted coding > Vibe coding

There's a difference.

[Codistry @codistryai]

@Reshad020 💯

[Codistry @codistryai]

@theohandsh Here for the comments... I'm curious to know how most are growing past the MVP stage.