My AI SVG Prediction Was Wrong
The speaker's prediction that Anthropic would excel at SVG creation proved incorrect. Instead, Astra and Soul demonstrated superior performance in creating SVG characters and cute illustrations.
Summary
In this brief transcript, the speaker reflects on an incorrect prediction regarding AI model performance in SVG (Scalable Vector Graphics) creation. The speaker initially predicted that Anthropic would outperform competitors, expressing uncertainty with qualifiers like "Perhaps?" and "Maybe Soul?" However, the actual results contradicted this expectation. Upon testing, both Astra and Soul produced notably better results than anticipated, specifically excelling at handling SVG characters and creating cute illustrations. The speaker concludes that for SVG creation tasks, Astra and Soul are the preferred models over what was initially expected from Anthropic.
Key Insights
- The speaker predicted Anthropic would deliver exceptional SVG creation capabilities but this prediction proved to be wrong
- Astra and Soul handled SVG character creation significantly better than expected or anticipated
- Both Astra and GPT Soul demonstrated superior capability in creating cute illustrations in SVG format
- For SVG illustration tasks specifically, Astra and Soul are the preferred models over other options
- The speaker expressed genuine surprise at the actual performance results compared to their initial hypothesis
Topics
Transcript
[0:00] I think Anthropic will blow everyone away in SVG creation. Perhaps? Maybe Soul? I don't know. This is a real surprise. Astra and Soul handled SVG characters much better. Astra and GPT Soul made these cute illustrations. So, it seems that for SVG, we prefer Astra and Soul in illustrations.
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
Warp agents open PRs to fix the factory itself
Programming agents can autonomously improve factory systems by analyzing failed launches and proposing specific updates to agent definitions. A self-improvement loop enables observer agents to detect failures and generate evidence-based modifications that prevent recurring issues, such as changing specific steps in factory agent procedures.
Humans are still the bottleneck in Warp’s AI factory
Warp discusses how human code review has become the main bottleneck in their AI-assisted software development process, with a 3.5-hour delay from PR to first human review compared to 35 minutes from launch to PR. They're evolving their workflow to reduce human dependency by allowing requesters to review agent-generated code themselves, and plan to eventually skip review entirely for low-risk tasks by treating code review as a risk management exercise.
I Quit Claude Because It Was Annoying
The speaker explains why they stopped using Claude, citing frustrations with its tendency to produce nonsensical output and communicate in an unnatural, non-human manner. They mention considering a switch to Opus 5.5 but remain uncertain about fully migrating their work tasks.
Claude Is Not a Party Boy
A humorous character description of Claude as someone with traditional values who prioritizes work over social indulgence. The transcript portrays Claude as principled, occasionally frustrating, and willing to push back on tasks he finds objectionable.
Claude Is Back. I Still Reach for Codex.
The speaker explains their preference for using Codex over Claude, citing superior tooling, a better desktop application, and specific strengths in front-end design and SVG work. Despite Claude's return, they continue to reach for Codex for their development needs.