Research library
Software engineering
Practical architecture and development decisions for software that people can use, maintain, and adapt.
108 articles · Page 7 of 9
Claude Sonnet 5: Anthropic Cuts the Price and Closes the Gap to Opus
Claude Sonnet 5 ships at $2/$10 launch pricing as the most agentic Sonnet yet. The real story: the gap to Opus 4.8 and a new tokenizer.
How AI Finds Vulnerabilities: Fuzzing, Reasoning, and Validation
How AI agents find software vulnerabilities: hybrid fuzzing, static analysis, LLM reasoning, validation, benchmarks, and patch workflows.
OpenAI's GPT-5.5-Cyber and Codex Security: Defensive AI Moves Into the Commit Stream
OpenAI's GPT-5.5-Cyber and the Codex Security plugin move defensive AI from the chat window into the commit stream. What the AISI benchmarks really show.
Why Every AI Lab Suddenly Ships a Coding Agent
In two weeks Anthropic, OpenAI, Microsoft, and xAI all shipped or expanded terminal coding agents. The convergence tells you where AI's value now sits.
Microsoft Build 2026: Seven MAI Models and the Quiet Exit From OpenAI
At Build 2026 Microsoft shipped seven in-house MAI models — reasoning, coding, voice, image — built to cut OpenAI dependence and undercut rivals.
Project Glasswing's First Month: 10,000 Vulnerabilities Found, and Why That Was the Easy Part
Anthropic's Project Glasswing found 10,000+ high-severity flaws in a month via Claude Mythos Preview. Finding bugs got cheap; fixing them didn't.
OpenAI's Codex Update: Goal Mode Graduates and Codex Reaches Off the Terminal
Codex's May 21 update takes Goal Mode out of beta, adds macOS Appshots and remote desktop control, and opens a plugin marketplace to Business users.
TPU v8 vs Blackwell: How AI Silicon Is Splitting Into Training and Inference Chips
Training and inference need different silicon. TPU v8t/v8i architecture, comparison to Blackwell's unified design, and per-token cost implications.
OpenAI Ships Codex in the ChatGPT Mobile App — The Phone Becomes an Agent Remote Control
Codex now runs in the ChatGPT mobile app as a remote control for macOS agents — the phone supervises while code and credentials stay on desktop.
Compressed Sparse Attention: How DeepSeek V4 Reached 1M Context at 27% of the FLOPs
DeepSeek V4 hits 1M context at 27% of V3.2's per-token compute. How Compressed Sparse Attention and Heavily Compressed Attention combine to do it.
KV Cache: The Hidden Memory Wall in LLM Inference
The KV cache memory wall in LLM inference: the math behind long context costs and architectural solutions (GQA, MQA, MLA, paged attention).
Anthropic Launches Claude Design — Figma Drops 7% the Same Day
Claude Design generates prototypes, slide decks, and mockups from plain prose, imports design systems, and triggered a 7% Figma stock drop.