#编码

The coding interview is dead, at least for my team at Anthropic. I've seen enough to know that it no longer provides signal. I removed it from loops this month. I have a spicy, optimistic take - I think there's an opportunity for junior engineers: https://felixrieseberg.com/hunger-beats-tenure-advice-for-junior-engineers/

verification is the biggest bottleneck for coding agents right now according to @addyosmani. we @warpdotdev have put a lot of thought into building a good computer-use tool for Warp Factories. every agents gets a computer to navigate the apps they built, take screenshots and recordings, and post them back for human review. 3-4mins of activity get edited down to 15 clips stitched together with cursor clicks, mouse animations, and key presses. we've been able to dramatically cut our time to merge and unlocked faster iteration + review cycles, especially for projects that are hard to mock out locally!

Codex is one of the most important untold stories in the history of technology. A year ago, it was a scrappy effort in a quiet corner of @OpenAI. Its cloud product hadn’t found PMF, and the team was starting over from scratch. Less than 12 months later: - Codex swallowed the flagship ChatGPT desktop app from the inside (it literally runs as com.openai.codex on your Mac) - Codex and ChatGPT for Work hit 40M+ weekly users across engineering and knowledge work - Its leader @thsottiaux was elevated to run all of OpenAI’s core products, including ChatGPT, Codex, and the API How did they pull it off? They trained their own dedicated model line, separate from ChatGPT, with researchers and product builders sitting on the same team They built four different products in a single year (cloud → terminal → IDE sidebar → a desktop app with no code editor at all) as every model leap made a new form factor possible They used Codex to build Codex—so a handful of people could prove a new product in weeks instead of arguing for it in meetings I had a front-row seat to the whole arc—from their failed Cloud launch, to OpenAI’s offices the night before GPT-5 dropped, to the day Codex took over ChatGPT. And I spent months interviewing @gdb, @thsottiaux, @embirico, @mia_glaese, @aambrosino, and @edbayes to get inside how it all went down. Here is the full, behind-closed-doors story of the team that remade OpenAI: https://every.to/p/how-codex-happened We’re pushing the boundaries of how stories like this are told. This piece is completely agent-native—designed to be read alongside your agent inside ChatGPT’s in-app browser: - Every interview transcript is included in full: Click any quote and you (or your agent) can see the exact conversation it came from. - Built for your agent to explore: Ask your agent to pull out product lessons for your team, cross-examine the transcripts, or find insights I missed when writing the piece. It’s a story about the future of software—built to be read with an agent: https://every.to/p/how-codex-happened

We rebuilt TasteSkill from scratch And today we are introducing TasteSkill v2 v2 gives your coding agent an art direction, assets and a browser check to verify its work npx skills add Leonxlnx/taste-skill check out more examples below!

codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software. swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go. admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?". well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is: • correct • bug free • fast and cost efficient to run it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start. but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing! agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale. the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree

codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software. swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go. admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?". well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is: • correct • bug free • fast and cost efficient to run it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start. but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing! agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale. the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree

Now in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of the most loved new features we've ever tested internally.

Power users are driving consumer AI market growth. The top 1% of US consumer AI payers average $903 a month, while flat plans hold the median at $25. One top-1% payer spends as much as roughly 59 bottom-half payers, on average. Median spend has barely moved, while average spend in the top 1% climbed from $504 to $903 a month between January 2025 and August 2026. Model labs are better placed than apps built on their models to capture consumer AI's top 1% of spenders. Those users average $903 a month, up from $504, and most of it buys model usage. A lab pays only its serving cost for that usage, while an app pays API prices. Anthropic earlier said one $200 Max subscriber ran up tens of thousands of dollars in usage, a bill no API-paying app could absorb. Apps that want this tier have to own more of the model, as Cursor began doing with its Composer coding model.

OpenAI recently published data on its researchers’ coding-agent usage. We took their weekly figures from January to mid-August 2026 and fitted trends to summarize how quickly spending grew. We found that spending has been doubling about once a month.