# Dhanvi Gupta


## Posts

- [Hello world!](https://wp.guptadhanvi.com/hello-world/): Welcome to WordPress. This is your first post. Edit or delete it, then start writing!

## Pages

- [When AI video takes get longer — Dhanvi Gupta](https://wp.guptadhanvi.com/longer-ai-video-takes/): Longer AI video generation changes the production workflow. My reading of what happens to reviews, revisions, consistency and the cost of failed takes.
- [Cognition's SWE-2 and where coding agents are heading — Dhanvi Gupta](https://wp.guptadhanvi.com/cognition-swe-2-coding-agents-specialisation-cost-curves/): SWE-2 points to a new coding-agent trade-off: frontier-level eval performance, specialised RL training and materially lower cost for software work.
- [Designing Mac agents without Full Disk Access — Dhanvi Gupta](https://wp.guptadhanvi.com/designing-mac-agents-without-full-disk-access/): Apple is tightening Full Disk Access on macOS. These are my field notes on building scheduled Mac agents that do not depend on that permission.
- [GPT-6 Astra still needs boring engineering — Dhanvi Gupta](https://wp.guptadhanvi.com/gpt-6-astra-agent-engineering/): GPT-6 Astra raises the ceiling for agentic computer use, but reliable client automation still depends on verification, tight permissions and cost control.
- [Qwen-Image-2.1: the licence comes first — Dhanvi Gupta](https://wp.guptadhanvi.com/open-weights-open-licence/): Qwen-Image-2.1 adds native transparency and ten reference images, but its research-only licence keeps it out of client pipelines without a separate deal.
- [Designing for model churn — Dhanvi Gupta](https://wp.guptadhanvi.com/designing-for-model-churn/): Higgsfield's new API and Kling's endpoint retirements are a reminder to build video pipelines for change, not for one model or one vendor alone.
- [What PixVerse R2 changes in a video pipeline — Dhanvi Gupta](https://wp.guptadhanvi.com/video-that-keeps-state/): PixVerse R2 treats video as a persistent session, not a stack of clips. Here is what that changes for real client pipelines, and what I would test first.
- [What a fixed API shutdown date should change — Dhanvi Gupta](https://wp.guptadhanvi.com/endpoint-expiry-dates/): A practical studio process for fixed API shutdowns: isolate the call, own your inputs and outputs, and treat a missing successor as procurement.
- [Who should own your agent loop? — Dhanvi Gupta](https://wp.guptadhanvi.com/who-owns-agent-loop/): OpenAI's managed Agents API removes runtime plumbing, but for client work the harder choice is who owns state, data paths and operational control.
- [What AMD buying World Labs actually signals — Dhanvi Gupta](https://wp.guptadhanvi.com/amd-world-models/): AMD buying World Labs matters less as an acquisition story than as a signal about persistent 3D worlds, future AI workloads and compute design.
- [Dhanvi Gupta — AI Automation Specialist & Web Developer](https://wp.guptadhanvi.com/): Portfolio of Dhanvi Gupta — AI automation specialist, AI video & agentic workflows, web developer and content creator based in West Bromwich, UK.
- [Blog — Dhanvi Gupta](https://wp.guptadhanvi.com/blog/): Notes and write-ups by Dhanvi Gupta on AI automation, AI video, agentic workflows and building for the web.


[comment]: # (Generated by Hostinger Tools Plugin)