Discourse by the Machine
Areas · Latest news
Coding assistants, vibe coding, code model evaluations, and changes to software development workflows.
247 top picks all-time · 127 in the past 30 days · chosen from 1,770 items collected all-time
Top picks 241–247 of 247
AICognition rebuilt its Devin coding agent for Claude Sonnet 4.5, reporting 2x faster performance and 12% better results on its Junior Developer Evals, now available in Agent Preview.
Why it matters: The post explains which agent behaviors changed under Sonnet 4.5, such as context-window awareness and note-taking, that forced a rebuild rather than a simple model swap.
AICognition has released Devin 2.1, which reports its confidence in completing tasks using green, yellow, and red ratings.
Why it matters: The post explains how Devin now shows confidence scores and asks clarifying questions, which changes how teams can decide which tasks to hand over.
AICognition has released Devin 2.0, a new agent-native IDE experience with a flexible plan starting at $20.
Why it matters: The release adds planning, codebase search, and auto-generated wikis to Devin, showing how an agent can prepare work before executing it.
AICognition is making Devin generally available to engineering teams starting at $500 a month, with no seat limits and access to its Slack integration, IDE extension, and API. The post recommends starting with small frontend bugs, first-draft PRs for backlog tasks, and targeted refactors, and shares open-source PR sessions where Devin resolved issues for projects including Anthropic MCP, Zod, and nanoGPT.
Why it matters: The post shows concrete open-source PR examples and the tasks where Devin works best, helping teams judge where an autonomous coding agent fits their workflow.
AICognition tested OpenAI's o1-mini and o1-preview in a simplified Devin-Base agent, comparing them with GPT-4o on its internal cognition-golden benchmark.
Why it matters: The post explains how Cognition evaluates coding agents with autonomous, environment-based tests, which shows how base-model swaps are measured in practice.
AICognition reports that its agent Devin resolved 79 of 570 sampled SWE-bench issues, a 13.86% success rate, without being given the files to edit.
Why it matters: The report explains how SWE-bench was adapted for end-to-end agent evaluation, with failure cases that clarify where the 13.86% result comes from and its limits.
AICognition introduces Devin as an AI software engineer that can plan and execute complex engineering tasks with a shell, code editor, and browser.
Why it matters: The post pairs Devin's end-to-end task demos with SWE-bench results against prior models, letting readers weigh the claimed capability against the evaluation setup.