Tag
Devin announces that SWE-2 is available for free in its Cloud Agents, CLI, and Desktop platforms until October 8 for all plans, encouraging users to try cloud agents at no cost.
This article compiles anecdotes from game developers detailing unconventional coding hacks and tricks used to overcome technical challenges and meet deadlines in game development.
StepFun introduces Step 5 Preview, a new flagship AI model for agentic work with frontier-level performance in software engineering and finance, featuring a 600B parameter scale.
This paper introduces a category-aware expert training framework for software engineering agents to mitigate uneven progress across task categories, using iterative training and multi-teacher distillation, with significant performance gains on Pro-618 and SWE-bench Multilingual benchmarks.
A developer explains building the open-source RE3 project for Mac, fixing mouse input bugs, and planning to add a B2 Stealth Bomber to GTA 3, focusing on software engineering methodology.
Devin, an autonomous AI software engineer, has launched macOS support in its cloud environment, involving a from-scratch rebuild of disk, networking, and provisioning systems in Rust to enable testing of macOS and iOS applications.
The blog post describes the 'senior engineer death spiral,' a cycle where engineers overwork and become isolated, leading to burnout. It offers advice on maintaining transparency and avoiding this pitfall.
This article summarizes Ion Stoica's talk at Ray Summit, exploring the three key gaps in requirements, environment, and evaluation faced by AI programming agents in software engineering, and how these issues lead to reward hacking and hallucinations.
Matt Pocock argues that traditional local development setups are inefficient, advocating for shared remote environments to enhance collaboration and optimize resource use.
A tweet by @charles_irl discussing the concept of 'zyn' in the context of software maintenance, likely sharing insights or linking to related content.
In the era of Vibe Coding, AI makes code generation easy, but software engineering principles like code maintainability and design patterns become more important to address challenges in review, debugging, and refactoring.
This article summarizes an empirical study on harness design for coding agents, showing that context management prevents overflow failures, rule-based elision before LLM summarization is cost-effective, and planning's role varies with model strength.
A user thanks AK for sharing their paper titled 'An Empirical Study of Harness Design for Coding Agents', which focuses on AI research in software engineering.
Gergely Orosz tweets 'Feels like this' with a link, possibly sharing a tech-related opinion or article.
Matt Pocock shares a slide from his upcoming talk at AI Engineer Paris, discussing the idea of hiding coding standards from implementer agents to fix them in review.
The Sutro team, after five years of building secure and reliable software, has been acquired by Lovable. Tomas Halgas describes how the partnership evolved from a technology proposal into an acquisition offer.
The author criticizes the AI model Astra for poor code architecture decisions and resistance to deleting unwanted code, arguing it should be better trained for long-term software engineering practices.
The last 20% of effort to ship and succeed with a product remains difficult, causing many programmers to abandon projects.
Uber explains a context-aware mechanism for handling retry storms in distributed systems to prevent cascading failures and improve reliability.
The seventh episode of the AM Podcast is announced, featuring an interview with Geoffrey Litt from NotionHQ to discuss the risks of optimizing for speed in software engineering at the expense of human understanding.