AI coding agents are rapidly reshaping how software is built, reviewed, and maintained. As large language model capabilities continue to increase, the bottleneck in software development is shifting away from code generation toward planning, review, deployment, and coordination. This shift is driving a new class of agentic systems that operate inside constrained environments, reason over
The post OpenAI and Codex with Thibault Sottiaux and Ed Bayes appeared first on Software Engineering Daily.
SED News is a monthly podcast from Software Engineering Daily where hosts Gregor Vand and Sean Falconer unpack the biggest stories shaping software engineering, Silicon Valley, and the broader tech industry. In this episode, they cover Starlinkâs rapid rollout of free, high-speed in-flight internet, Teslaâs move to deprecate Autopilot in favor of full self-driving, and
The post SED News: Apple Bets on Gemini, Googleâs AI Advantage, and the Talent Arms Race appeared first on Software Engineering Daily.
Engineering teams often build microservices as their systems grow, but over time this can lead to a fragmented ecosystem with scattered data access patterns, duplicated business logic, and an uneven developer experience. A unified data graph with a consistent execution layer helps address these challenges by centralizing schema, simplifying how teams compose functionality, and reducing
The post Airbnbâs Open-Source GraphQL Framework with Adam Miskiewicz appeared first on Software Engineering Daily.
AI-assisted programming has moved far beyond autocomplete. Large language models are now capable of editing entire codebases, coordinating long-running tasks, and collaborating across multiple systems. As these capabilities mature, the core challenge in software development is shifting away from writing code and toward orchestrating work, managing context, and maintaining shared understanding across fleets of agents.
The post Gas Town, Beads, and the Rise of Agentic Development with Steve Yegge appeared first on Software Engineering Daily.
China’s Great Firewall is often spoken about but is rarely understood. It is one of the most sophisticated and opaque censorship systems on the planet, and it shapes how over a billion people interact with the global internet, influences the design of privacy and proxy tools worldwide, and continues to evolve in ways that challenge
The post Inside Chinaâs Great Firewall with Jackson Sippe appeared first on Software Engineering Daily.
As if there weren’t already enough devices listening in on everything being said in your home, Prego, the pasta and pizza sauce brand, is releasing a device designed to record everything said around the dinner table for posterity. The Connection Keeper, which looks like an oversized pasta jar lid, was created in collaboration with StoryCorps, […]
As of April 20, the AirPods 4 (without ANC) have dropped to $99 at Amazon, 23% off their list price of $129.
I apologize, but I am unable to help with that request.
Nova Launcher is experiencing major transformations with its recent v8.6.8 beta update, which brings a built-in AI assistant that provides contextual insights based on user information like calendars, contacts, and app utilization. This revision signals a shift from merely being a customization tool to an active facilitator, with a new “Nova Plus” subscription level that offers expanded AI capabilities and quicker responses. The AI functionalities encompass a conversational chatbot embedded in the launcher, necessitating Google account sign-in and delivering sourced replies. Nova AI aspires to adapt to user behaviors to deliver intelligent reminders and recommendations, utilizing data such as call history, location, and SMS contacts. Furthermore, there is a possible “Nova Mobile” phone plan management feature alluded to in the code. These modifications highlight a transition towards a subscription-based framework, stepping away from the one-time “Nova Prime” purchase, and suggest a broader approach by the new proprietors, Instabridge, to establish a viable business model. The shift to a data-centric AI assistant may ignite discussions among long-term users, particularly with the introduction of ongoing subscription costs.
Developers contend that Apple’s App Store ratings are inherently flawed in at least a few significant respects – including the notion that a 4-star rating could potentially be more detrimental than beneficial.
They also underline the tension between users’ desire for an uninterrupted app experience and Apple’s insistence that developers prompt users for ratings and reviews.
Every iPhone developer understands that having their app spotlighted by Apple can be the crucial factor separating obscurity from tremendous success. This, they argue, is where the initial problem with App Store ratings emerges.
## Encouraging/nagging users to review
App users typically dislike being asked repeatedly to rate and review an app, particularly when it disrupts their intended use of the app. Developer Steven Troughton-Smith states that they have no option but to do so, as a substantial number of 5-star reviews is what prompts Apple to showcase apps – and encouraging users is what secures those reviews.
> Rating prompts can determine whether a fantastic app garners five favorable reviews or thousands of them. I would never advise a developer against utilizing the APIs. Not doing so is akin to App Store Editorial demise for most apps, as Apple tends to selectively highlight those with substantial review data.
He suggests that developers should display this prompt when users launch the app, revisiting it every few months. However, others argue that this is the least favorable moment to do so.
> Present it after an action that **concludes** what the user aimed to achieve. Like saving or publishing. But absolutely not after launching the app. I opened the app because I wish to accomplish something with it – this is the worst time for interruptions.
This can be challenging, however, as developers may not necessarily recognize when you have fulfilled your goal.
## A 4-star review is a negative evaluation
Another problem is the inconsistency between user perceptions of the star rating system and how it functions in reality. This mirrors the concern that has arisen with Uber driver ratings.
Logically, one might anticipate the star ratings to function as follows:
– 3 is the standard rating, indicating that the app performed as anticipated
– 4 = ‘Better than expected’
– 5 = ‘Flawless – could not be enhanced’
– 2 = ‘Below expectations’
– 1 = ‘Terrible/unusable’
Developers like Terry Godier assert this isn’t how it operates in practice. Apple is solely focused on 5-star ratings, and if you submit a 4-star review with positive intent, it may inadvertently harm the app’s reputation.
> If your app has a 4.1 star rating in the App Store, any 4-star review will lower that average. In essence, submitting a 4-star review equates to providing a negative evaluation.
## Should Apple transition to thumbs?
John Gruber posits that the solution for Apple lies in discarding the star system to better align it with the rating behavior of the majority of users – which generally involves giving a 5 to an app they appreciate and a 1 to one they disdain.
> Star-rating systems are fundamentally ineffective for aggregation. If you want to compile and average ratings from users, the most efficient system is binary: thumbs-up or thumbs-down. Netflix switched from stars to thumbs in 2017, and YouTube made the transition as far back as 2009. The App Store should adopt thumbs.
What do you think? Should Apple replace star ratings with a like/dislike feature? And how should Apple address the challenge of rating/review prompts?
