Developer Runs Indie Studio Remotely Using AI Agents and Voice Mode All Day

·1 views

A solo developer at HoneyDrunk Studios spent a full workday managing studio tasks from his couch using AI agents and Codex in voice mode, directing work through conversation rather than hands-on coding. During that session, 61 public NuGet packages were updated, published, and verified, with agents handling the dependency chain sequentially while he remained available for decisions. He also integrated Claude Code into the workflow after completing authentication and configuration steps, then used it to generate a Blender scene — including objects, lettering, and a short animation — based on verbal descriptions. The process involved interruptions, repeated instructions, and setup friction, but allowed ordinary life to continue alongside studio progress. The developer framed the experience as a notable shift in how independent software work can be structured when agent-based tools handle the gaps between key decisions.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Developer Builds AI Tool to Generate ASL Sign Videos, Flags Accuracy Concerns

A developer with years of ASL experience has created SignBridge, a prototype that uses generative AI to produce videos of individual American Sign Language signs. The tool accepts a word as input and attempts to generate a corresponding signing video, using detailed prompts about handshape and movement. However, the creator acknowledges a key limitation: generated videos can appear convincing while containing errors in handshape, position, or motion, and results vary across generations. Sentence-level signing remains out of scope for now, with the project focusing solely on single words. The developer is seeking input from experts in pose estimation, animation, and sign language technology, with a preference for verification methods involving Deaf signers rather than visual plausibility alone.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Developer launches Basya Entertainment to house browser games, tools, and oddities

A developer has launched Basya Entertainment, a personal platform consolidating a wide range of self-built projects including browser games, utilities, and experimental tools. The site features a curated 'Featured' section highlighting key projects such as BasyaNet, a custom browser, BasyaOS, a graphical desktop environment, and Doomaze, a browser-based maze game. Other offerings span casino games, puzzle collections, sandboxes, and an archive format called BEZip. The featured shelf was designed to give first-time visitors a clear entry point before they explore the broader catalogue. The developer has made the platform available at basya.org and is actively seeking feedback on clarity, discoverability, and overall user experience.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to Build a Personal Health Dashboard Using Grafana and TimescaleDB

A developer guide published on DEV Community outlines how to create a unified, self-hosted health data dashboard by combining data from Apple Health and Google Fit. The setup uses TimescaleDB, a PostgreSQL extension optimised for time-series data, alongside Grafana for real-time visualisation. A Node.js middleware layer normalises incoming JSON payloads from multiple health APIs into a consistent database format. The entire stack is containerised using Docker and Docker Compose, making it straightforward to deploy and scale. The project aims to give users full ownership of their biometric data outside proprietary platform ecosystems.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Adobe Campaign Classic Patches 18 Critical Flaws, Including a Perfect 10.0 CVE

Adobe fixed 18 critical vulnerabilities in Campaign Classic in September 2026, as detailed in security bulletin APSB26-142 and Dutch NCSC advisory NCSC-2026-0393. The flaws span OS command injection, SQL injection, server-side request forgery, and incorrect authorization, with ten requiring no authentication to exploit. The most severe, CVE-2026-75699, carries a maximum CVSS score of 10.0, making unpatched deployments a high-priority risk. The fully patched version is Campaign Classic 7.4.4 build 9402, with hosted environments already updated. Until patches are applied, administrators are advised to restrict access to Campaign Classic endpoints and limit outbound connections as interim mitigations.

0 comments Read more at DEV Community