Sign in Subscribe

Topic

Computer Science

A collection of 45 issues

One Record, Many Assertions

Agent evaluations tend to acquire a new expectation type for every capability: messages, tool calls, state changes, delegations, UI actions, memory, artifacts, audit logs. The result is usually a fragmented test system in which closely related requirements are represented and evaluated differently. A cleaner design separates three artifacts: trial record

The Example Store Is Model State

Consider a classifier that retrieves labeled examples for an incoming query and gives them to an LLM to choose a label. This is a form of k-nearest-neighbor classification with an LLM decision rule: the store supplies the examples and the LLM decides how they imply a label. More

From Vibe Coding Assistants to Coding Assistants

Modern coding assistants often firehose code: a single prompt yields pages of plausible implementation that the developer must reverse‑engineer, reconcile with project conventions, and defend in review. That behavior is optimized for vibe coding—outputs that look complete and fluent—rather than for actual coding, where teams must understand,

(Don't) Feed the Robots

"My site [with] modest traffic (~1,000 visitors per day) went from serving ~1GB/hr (to tons of AI crawlers!) to ~50MB/hr in traffic" Can you tell what was the point where I 1. Manually blocked a few AI crawlers 2. Moved my nameserver to Cloudflare plus

The GitHub Sampler

GitHub is the world's largest developer platform, making it a compelling place to build developer tools and study software development. However, with over half a billion repositories and an API that limits responses to a thousand results, it feels nigh impossible to answer even simple questions like, "

Coding At a Distance

Senior professors have long lived the future of coding. Professors ask. Underlings code. Professors critique the output, e.g., "I prefer statistical significance stars for the betas but not the constant term." Underlings revise the code. The cycle continues. Something similar can play out at companies. Now, thanks

Building Together, Separately: Challenges of Software Development

With Atul Dhingra Microservices, Macroproblems A single page on Doordash can make upward of 1000 gRPC calls (see the interview). For many engineers, upward of a thousand network calls nicely illustrate the chaos and inefficiency unleashed by microservices. Engineers implicitly diff 1000+ gRPC calls with the orders of magnitude fewer

American PII: Lapses in Securing Confidential Data

At least 83% of Americans have had their confidential data shared with a company breached (see here and here). The list of most frequently implicated companies in the loss of confidential data makes for sobering reading. Reputable companies like LinkedIn (Microsoft), Adobe, Dropbox, etc., are among the top 20 worst

Bad Service: Missing Functionality in Web Services

A host of cloud services are missing the core functionality needed to build businesses on top of the services. Powerful services on mature platforms like Google Vision, etc., have a common set of deficiencies—they do not allow clients to send information about preferred latency and throughput (for a price)

Reducing Friction in Selling Data Products: Protecting IP and Data

Traditionally, software has been distributed as a binary. The customer “grants” the binary a broad set of rights on the machine and expects the application to behave, e.g., not snoop on personal data, not add the computer to a botnet, etc. Most SaaS can be delivered with minor alterations