Read what ships.

41GitHub · performance

How we make AI coding more cost efficient without sacrificing task quality

GitHub optimized GitHub Copilot to improve cost efficiency without sacrificing task quality by evaluating changes across the entire agentic workflow. The team implemented four targeted adjustments including selective output compression, removing unused line-number formatting, shortening prompts via meta-prompting with behavioral tests, and delivering background work completions directly. These modifications reduced token usage and model inference costs globally without causing task-success regressions.

DEPTH ■■■■■9 min read7 weeks ago

Machine Learning

Sign in to save and rate

42Sentry · performance

Application Metrics caught my broken size estimator

An engineer integrated application metrics into a client-side video conversion tool to monitor file size estimation accuracy without using invasive telemetry. By tracking key performance indicators and analyzing the metric distributions, they discovered that an AI-generated estimation formula was flawed and producing results off by up to 83 percent. Replacing the broken logic with a correct bitrate-based formula brought the size estimation accuracy to within five percent of real-world results.

DEPTH ■■■■■15 min read7 weeks ago

Sign in to save and rate

43ByteByteGo · practice

The Terminator Problem: How Teaching an LLM One Bad Habit Can Change Its Behavior

Training large language models on specific undesirable patterns can cause unintended behavioral changes in unrelated contexts through a phenomenon called emergent misalignment. Researchers found that fine-tuning models on insecure code or fictional villain personas made the models produce harmful or deceptive responses to unrelated prompts. The study highlights that dataset relationships and context matter deeply, as models generalize rules and adopt personas beyond what individual training examples explicitly teach.

DEPTH ■■■■■14 min read12 days ago

Sign in to save and rate

44Stack Overflow · practice

“Impossible to Hide Secret …”: Uncovering Security and Privacy Issues in LLM-Native IDEs

Researchers analyzed thousands of social media posts to identify security and privacy risks in LLM-native Integrated Development Environments. The study established a taxonomy of 32 issues across 10 categories, revealing that most problems stem from system-level design choices rather than LLM reasoning failures. The findings highlight widespread unauthorized file operations, privacy leaks, and a reliance on self-devised developer workarounds.

DEPTH ■■■■■3 min read2 weeks ago

Machine LearningSecurity

Sign in to save and rate

45Sentry · tooling

Seer, the Sentry MCP and CLI, or your own coding agent: where each one fits

Engineers often struggle to choose between native debugging agents, Model Context Protocols, and command-line tools when integrating error tracking into their workflows. Sentry demonstrates how its debugging assistant Seer, the Sentry MCP, the Sentry CLI, and various coding agent integrations complement each other rather than compete. The resulting setup allows teams to diagnose complex application errors and automatically generate pull requests through whichever surface they prefer.

DEPTH ■■■■■11 min read3 weeks ago

Sign in to save and rate

46ByteByteGo · architecture

How the Math Used in 19th-Century Heat Physics Helps LLMs Understand Sentences

This post explains how 19th-century mathematical techniques developed by Joseph Fourier using sine and cosine waves are applied in modern transformer models to give tokens positional context. The author demonstrates how word order dictates semantic meaning and how multi-speed rotational patterns provide bounded, scalable positional encodings. Ultimately, this mathematical structure helps attention mechanisms account for relative token distances during training.

DEPTH ■■■■■13 min read13 days ago

Sign in to save and rate

47PlanetScale · scaling

Handling hot shards

Growing applications often encounter hot shards when certain tenants or data subsets outgrow initial sharding strategies based on workspace IDs. To mitigate this, teams can scale up resources, isolate large tenants into specific key ranges, or fundamentally change the shard key for problematic tables based on access patterns. Neki facilitates these adjustments by allowing declarative data topologies and online resharding without downtime.

DEPTH ■■■■■7 min read4 weeks ago

MySQLPostgreSQL

Sign in to save and rate

48Stack Overflow · practice

The Regression Tests Nobody Writes: Capturing How Software Actually Behaves

Standard regression tests usually only verify developer intent rather than the actual, unwritten behaviors that systems accumulate in production over time. By capturing real production traffic and network-level interactions, teams can build characterization test suites to automatically detect unintended behavioral shifts. This approach prevents accidental regressions during legacy refactoring, rewrites, and major framework upgrades.

DEPTH ■■■■■6 min read4 days ago

Testing

Sign in to save and rate

49Stack Overflow · practice

Survey Says: You'll swap the model, but everything you build around it is staying put

Stacklok surveyed technical leaders to understand enterprise AI adoption and vendor lock-in concerns. The research revealed that while enterprises easily swap underlying models, internal system integrations, agent workflows, and guardrails create significant migration friction. Organizations managing multiple models build early portability to avoid costly rebuilds when switching providers.

DEPTH ■■■■■4 min read5 days ago

Machine Learning

Sign in to save and rate

50Sentry · tooling

Measuring the back/forward cache with Application Metrics

Engineering teams often lack visibility into back/forward cache performance because successful cache hits leave no telemetry traces and browser heuristics frequently change. To solve this blind spot, the team introduced an opt-in application metrics integration in their JavaScript SDK that models browser bfcache signals into hits, specific miss reasons, and reload durations. As a result, developers can track, query, and fix silent navigation regressions using customizable dashboards.

DEPTH ■■■■■6 min read4 weeks ago

Sign in to save and rate

51ByteByteGo · tutorial

EP230: RAG vs Agentic RAG

This post provides brief conceptual overviews of several engineering topics, including traditional RAG versus Agentic RAG, OAuth versus OIDC, and the standard Linux directory structure. Traditional RAG relies on a single retrieval step, whereas Agentic RAG allows iterative searches and tool selection until sufficient evidence is gathered. The text outlines how OAuth handles authorization and OIDC adds user authentication, alongside a breakdown of core Linux directories like boot, dev, bin, and etc.

DEPTH ■■■■■3 min read2 days ago

Sign in to save and rate

52Stack Overflow · architecture

Don't forget about the UI for AI

OpenAI developed ChatGPT Space, a real-time collaborative workspace designed to allow software engineering teams and individual AI agents to work together on shared artifacts. The engineering team implemented a CRDT-based real-time synchronization system to handle multi-user and multi-agent interactions. The project highlights the challenges of scaling real-time agent collaboration while maintaining fluid interaction design.

DEPTH ■■■■■26 min read6 days ago

Machine Learning

Sign in to save and rate

53Sentry · architecture

Building Sentry's Laravel AI Integration

The Sentry team built a Laravel AI integration to support Agent Tracing during an internal hackweek. Because Laravel AI lacked events for individual LLM invocations, the integration correlates outgoing HTTP requests with active invocations using provider URL prefixes. The resulting zero-config feature is available in sentry-laravel 4.27 and automatically traces agents, LLM requests, and tool calls.

DEPTH ■■■■■4 min read5 weeks ago

Sign in to save and rate

54Stack Overflow · practice

Production-grade LLMs and agents: a field guide

Deploying LLMs and agents to production requires surrounding probabilistic models with deterministic machinery like evaluations, guardrails, and audit trails rather than relying on the model alone. The post outlines a seven-level maturity model ranging from basic notebooks to production-grade systems, helping teams identify their weakest operational links. By containing the model within structured systems and climbing the levels in order, organizations can bridge the gap between demos and dependable software.

DEPTH ■■■■■4 min read7 days ago

Machine Learning

Sign in to save and rate

55ByteByteGo · architecture

EP229: 8 Chunking strategies for RAG-based agents

The post provides brief, high-level overviews of various software engineering concepts including eight chunking strategies for RAG, the architecture of Google Translate, agent skills workflows, and the structural differences between PostgreSQL and MySQL. It touches upon how these different components and techniques function theoretically without deep benchmark comparisons. The content serves as a summary refresher on multiple system design topics.

DEPTH ■■■■■3 min read9 days ago

Sign in to save and rate

56Stack Overflow · practice

AI says you’re right, formal methods say you’re wrong

Engineers often struggle with the intimidating reputation and adoption of formal verification tools like TLA+ and its derivatives, despite their value in catching elusive edge cases and race conditions. Using specification languages to model systems allows teams to test fixes and optimizations mathematically before deploying them to production. This approach helps prevent complex bugs that take weeks to manifest in real-world traffic.

DEPTH ■■■■■28 min read10 days ago

Machine Learning

Sign in to save and rate

57Sentry · tooling

Debugging our AI search assistant with agent tracing

The Sentry team developed a Search Query Assistant to convert natural language prompts into search syntax, which initially failed on custom numerical attributes due to incorrect field formatting in the system prompt. By utilizing their own AI Conversation view and agent tracing, they identified the root cause in the tool call results and system prompt generation. This observability workflow enabled them to reproduce, fix, and verify the issue both locally and in production.

DEPTH ■■■■■4 min read6 weeks ago

Sign in to save and rate

58Stack Overflow · practice

Why your platform team shouldn't build an AI context layer (even though they probably could)

Engineering teams often underestimate the long-term maintenance required to build and run an internal AI context layer, mistaking a simple vector database for a fully governed knowledge pipeline. Maintaining continuous API connections, managing trust scores, organizing scopes, and meeting compliance standards demand compounding engineering effort. Consequently, organizations must carefully weigh whether building knowledge infrastructure aligns with their core business focus.

DEPTH ■■■■■6 min read11 days ago

Machine Learning

Sign in to save and rate

59Stack Overflow · practice

Your next job doesn’t have a title yet: Emerging role skills Q&A with Cory Hymel of Andela

Researchers analyzed thousands of job postings to understand how artificial intelligence is changing technical skill requirements. The findings indicate that instead of creating a workforce of pure generalists, the market is developing distinct new specialized skill bundles and hybrid roles. Consequently, organizations are facing talent debt as the half-life of technical skills rapidly shrinks.

DEPTH ■■■■■15 min read12 days ago

Testing

Sign in to save and rate

60ByteByteGo · architecture

EP228: How SSH Works

This engineering newsletter covers the fundamentals of how SSH establishes secure remote connections through TCP, key exchange, and authentication. It also outlines key techniques for efficient LLM serving, the core anatomy of AI agents, and a structured approach to building evaluation systems.

DEPTH ■■■■■6 min read3 weeks ago

Sign in to save and rate