Full-text search across 59346 articles. Combine with topic and date filters; results sorted by relevance.
A developer's analysis of Thariq Shihipar's Claude Code effort-level study finds that higher effort settings do not make the model smarter but instead increase self-verification and autonomous decision-making. In tests o…
Amap Platform general manager Cui Yong unveiled Qianyu, a no-code spatial-intelligence platform for building location-based AI agents, at Alibaba's 2026 Apsara Conference in Hangzhou on September 24th. Amap says Qianyu t…
A developer's breakdown of Claude Code's token pricing shows that prompt caching is the dominant cost lever: cache reads cost 0.1× base input while cache writes cost 1.25× (5-minute TTL) or 2× (1-hour TTL), and an expire…
Pirol-ai released Company as Code, an open standard and validator tool called charta that lets organizations describe goals, roles, processes and policies as plain markdown files in git so AI agents can follow them. The …
A developer behind the open-source CI checker rebar ran it against 28 public repositories and found three false positives, including a husky 9 hook-executable rule that misread how husky 9 generates hooks and a hardcoded…
TechNative released specgetty, an open-source terminal tool for reviewing OpenSpec change proposals and specifications, under the command `spg`. Specgetty is written in Go and optimized for response time, offering a proj…
Researchers posted a paper on arXiv on 21 Sep 2026 introducing Burnashev Adaptive Posterior Matching (BAM), a feedback-coding scheme for black-box LLM steganography that recasts covert communication as a sequential probl…
Linear said on September 21st that a CI overhaul ordered by co-founder and CTO Tuomas Artman cut runner time per test roughly in half while its test suite nearly quadrupled during 2026, with pull request wait time fallin…
Developer satmihir released gobag, an open-source plugin for Claude Code that checkpoints a session's context, decisions, and pinned Git commits into a single encrypted .gobag file for restore on another machine. The plu…
A nine-author study led by Fan et al. held the underlying model and execution loop fixed while varying three coding-agent harness components — planning, action space, and context management — across 176 matched configura…
A developer reported that a local model, Ternary Bonsai 2, generated the parse_prompt function returning ParsedPromptInfo from a 180-line Markdown specification in about 30 minutes, producing 300-400 lines of Rust with 3…
An attacker who compromised a maintainer's GitHub account pushed malicious commits directly through the project's legitimate release pipeline, producing npm packages with valid provenance signatures that spread to hundre…
Docker Sandboxes introduce a new trust boundary for AI coding agents by running them inside a microVM with its own kernel and Docker Engine, mediating host access through explicit workspace, credential, network, skills, …
A September 17, 2026 arXiv paper (2609.20822v1) reports that coding agents tasked with robot manipulation collide with a forbidden obstacle in most cases because the safety constraint never becomes a planning priority, n…
A non-engineer growth marketer at Publora described building three Claude Code routines to automate a 10 a.m. analytics brief, a Monday/Wednesday/Friday content-idea backlog, and a twice-daily Hacker News digest. The rou…
A developer running a Claude Code-based engineering shop replaced an unenforceable writing style rule with a mechanical linter that flags unglossed internal jargon, after the original rule went 68 days without being foll…
A developer built pi-jev-auto-mode, an extension that gates the Pi terminal coding agent's bash, write, and edit calls through a rule layer plus TypeSafe's Jev decision-only probability model, which returns calibrated sa…
A developer measured whether coding agents actually follow the rules stored in their memory, finding that retrieval works but compliance does not: across 89 sessions, a pointer instructing the agent to read a rules file …
A developer released taskpods, a dependency-free Python CLI that uses Git worktrees to give each coding-agent task its own working directory, branch, and index within a shared repository. The tool wraps any agent command…
A developer detailed the "rubber stamp effect," a systemic failure in which AI code reviewers trained on mostly trivial diffs learn to approve changes with generic comments like "LGTM" while missing real defects. The wri…