Fetching from the wire…
01
02
03
04
05
06
07
08
Vibe Coding2026-08-08 · source-backed
In the same Willison session, oversized black spheres floated above each raccoon's head. Instead of inspecting code he asked "Why do the raccoons have huge black spheres on them?" then "Fix it." Done. I do this constantly now and it still feels like cheating. Describing the visual symptom gives the model a search target in a space you can't grep, and my design brain is better at naming what looks wrong than my engineering brain is at guessing which line caused it.
Each link below shares sources, entities, or timing with this story.
Simon Willison found it in the OpenRouter price list. 1.6T MoE, ~49B active, 1M context, up to 384K output, at $0.435/M input (cache miss) and $0.87/M output. The agentic-coding deltas versus the preview are the story: DeepSWE 12.8 → 62.7, CyberGym 52.7 → 83.3, Terminal Bench...
Here's the one you can act on today. DSPy shipped 3.3.0b1 with a new ReActV2 module, and if you're still hand-tuning prompt strings, you're doing manual labor a compiler should do. You declare a task as a typed Input to Output signature, pick a reasoning strategy, and MIPROv2...
A month ago, TeamPCP compromised Trivy's GitHub Actions runners. Then they trojanized LiteLLM on PyPI. Now Wiz Research confirms they've expanded to npm via a worm called CanisterWorm, using stolen publish tokens to push malicious packages across JavaScript's package ecosystem...
New chapter in the Agentic Engineering Patterns guide argues that refactoring tasks once "conceptually simple but time-consuming" (API redesigns, nomenclature cleanup, code consolidation) are now economically feasible via background agents. Reframes the quality debate from "AI...
simonwillison.net — Four models now above 80% SWE-bench (Opus 4.6 at 80.8%, Gemini 3.1 Pro at 80.6%, GPT-5.3-Codex at 80.0%, Kimi K2.5 at 76.8%). Willison's analysis: we're approaching the ceiling where SWE-bench stops being a meaningful differentiator. The gap between models...
$1.25 input / $4.25 output per million tokens for the standard tier. $0.10 / $0.20 for the Contributor tier, where Meta trains on your usage and feedback. That's roughly 12x on input, 21x on output, and it's the clearest number anyone has published on what your proprietary sou...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.