Tag
Databricks shares results from an internal benchmark evaluating coding agents on their multi-million line codebase, revealing capability tiers and cost-performance tradeoffs, and highlighting the effectiveness of open models like GLM 5.2.
Boris Cherny, creator of Claude Code, describes a workflow where he no longer writes code directly but prompts Claude, and often has one Claude prompt other Claudes, highlighting the immense leverage AI provides to individual engineers.
Discusses the Lindy effect in software, arguing that older, battle-tested technologies are often more reliable and lower-risk than trendy new ones.
The author describes their favorite software engineering interview question: computing the median of an array. They discuss the various angles it offers for evaluating candidates' programming skills, including sorting, edge cases, API design, and statistical understanding.
The article explores how AI agent workflows are reintroducing software engineering challenges around reproducibility, auditability, and state management that were previously solved with version control, CI/CD, and static code practices, while noting emerging solutions like GitHub's Agentic Workflows and git-native approaches.
Kent C. Dodds shares a podcast episode with Lucas Wargha discussing product engineering, user conversations, and engineering culture.
A roundup of benchmarks including SWE-Bench Pro and 312 real-world workflow tasks, likely evaluating AI performance on software engineering challenges.
A blog post introducing a series critiquing the overuse of acronyms in software engineering, exploring cultural and marketing reasons for acronym fatigue.
This article examines the gap between hype and reality for AI coding agents, arguing that they are effective for accelerating workflow parts but still require human oversight for architecture, debugging, and review, and questioning whether current benchmarks measure the right things.
A Twitter thread by Katelyn Lesse arguing that teams should confront the hardest part of a project head-on rather than avoiding it incrementally, illustrated by the story of Stripe's v2 accounts.
The author argues that fetching dependencies directly from VCS (as done in Go) is more secure and easier to audit than using package registries with a publish step (as in Ruby, npm, PyPI).
Argues that software engineering will always be necessary because human accountability is required to ensure AI builds safe and correct systems.
A speculative discussion questioning whether AI will render software engineering obsolete by mid 2026.
A tweet observes that new grad software engineers are relying on Fable 5 rather than understanding the codebase, highlighting a potential issue in software development practices.
A software engineer with 20 years of experience praises Fable's code-writing abilities, calling it exceptional and predicting significant change, while also noting the need for competition to OpenAI due to high costs.
An essay exploring why many developers struggle to use git properly, covering common mistakes like panic over merge conflicts, huge commits, and poor branching practices, and examining the root causes.
Rohan Paul discusses Tesla's reported AI spending budget of $800/month per software engineer, suggesting it sets a new benchmark. Chamath Palihapitiya comments that spending above $200/week is waste if Tesla is doing this.
Dan North proposes the 'Best Simple System for Now' (BSSN) approach as a middle path between quick-and-dirty and over-engineering in software development, advocating for simplicity that meets current product needs.
The author shares their experience switching from using superpowers to mattpocock/skills, compares the pros and cons of the two AI programming skill sets, emphasizes that mattpocock/skills saves more tokens and is more flexible, and discusses the evolution direction of AI-assisted software engineering.
An academic debate on whether computer science belongs to mathematics, citing a quote from computer science giant Knuth, involving discussions on discrete mathematics and the essence of algorithms.