Cognition Labs replaced Opus 4.8 with Fable 5 in its Devin coding agent and found that Fable-led runs cost less than Opus-led runs when using the Fusion sidekick architecture, despite Fable costing tw…
Kiro, a spec-driven development agent that writes specs, auto-generates tasks, implements code, and automates DevOps workflows, has been listed in the coding agents category. The tool competes with al…
Anthropic launched Claude Code, a terminal-first agentic coding tool with Computer Use integration, multi-file edits, persistent shell sessions, Git operations, and fine-tuning support. The tool compe…
Cognition Labs launched Devin, the 'first AI software engineer,' in March 2024 with a benchmark score of 13.86% on SWE-bench, but independent evaluations later showed it failed 14 out of 20 real tasks…
Cognition released SWE-1.7, an AI model that nearly matches the software engineering capabilities of frontier models like GPT-5.5 and Claude Opus 4.8 at a fraction of the cost, challenging the notion …
Cognition launched SWE-1.7, a new AI model that achieves frontier-level intelligence at a fraction of the cost, outperforming many competitors on software engineering benchmarks. The model was trained…
AI agents differ from chatbots by placing an LLM inside a loop where the model decides when to stop, enabling autonomous task completion. The progression from single LLM calls to function calling, cha…
Kotro Labs released Kotro Proxy Engine, an open-source Rust sidecar that acts as a local AI governance layer to reduce token usage and prevent runaway costs in agentic coding workflows. The tool featu…
Boris Tane argues that current AI agents are reactive, requiring human prompts to act, and announces his company's bet on proactive agents that autonomously find and execute work without human instruc…
Vercel CEO Guillermo Rauch discussed the company's role in AI software, noting that half of its 6 million daily deployments are triggered by coding agents and over 1 trillion tokens flow through its A…
A developer at archive.com describes why they cannot use Claude Code's scheduled agents on their real codebase due to accumulated technical debt from three design systems and undocumented business rul…
Developer Aakash Desai released CTOP, a terminal pane for monitoring AI coding agents including Claude Code, Codex CLI, OpenCode, and Devin, providing real-time CPU, memory, token usage, context windo…
A developer explains that prompt engineering is being replaced by agentic loops, where AI agents autonomously plan, edit, test, and fix code until tests pass, then open a pull request for human review…
Japan has become a fast adopter of AI coding tools like Cognition AI's Devin, driven by a shrinking workforce and aging legacy infrastructure. The country faces a projected shortage of 789,000 softwar…
Vincent van der Meulen reported that Claude Fable 5 generated over 60 ready-to-merge pull requests overnight when used as an orchestrator for autonomous coding agents, a claim that highlights a shift …
A developer created a middle manager agent for an autonomous software factory that orchestrates Devin coding sessions, manages an issue tracker, and communicates via Slack. The agent operates continuo…
Cognition CEO Scott Wu criticized token leaderboards for ranking engineers by AI token usage, calling them 'directionally correct' but prone to abuse. He argued that companies should instead measure a…
Greptile, Cursor, and Devin have agreed that AI coding agents should run their code for runtime verification, with the specific execution environment playing a critical role in ensuring reliability at…
The HALLUCINATE.md Foundation has released an open standard file, HALLUCINATE.md, that instructs AI coding agents not to hallucinate. The minimal specification, consisting of the directive "Do not hal…
At AI Native DevCon London, engineering leaders from various organizations discussed the shift from individual AI coding tools to enterprise-wide agent governance. The roundtables highlighted that whi…