Technique 3: Few-Shot with Negative Examples Anthropic discovered that showing the model what NOT to do is as powerful as showing what TO do. Template: I need you to [task]. Here are examples: GOOD Example 1: [example] GOOD Example 2: [example] BAD Example 1:
MACHINE LEARNING
-
6D Parallelism: The Human-like Parallel Processing in AI
By
–
Little-known fact in AI: 6D parallelism is human parallelism
-
BulletTime: Decoupled Control of Time and Camera Pose for Video
By
–
BulletTime
— AK (@_akhaliq) 5 décembre 2025
Decoupled Control of Time and Camera Pose for Video Generation pic.twitter.com/AwLyi6DvToBulletTime Decoupled Control of Time and Camera Pose for Generation
-
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
By
–
NeuralRemaster
— AK (@_akhaliq) 5 décembre 2025
Phase-Preserving Diffusion for Structure-Aligned Generation pic.twitter.com/y2m7LhcUS8NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation
-
Deep Think Mode Outperforms Gemini 3 Pro on Complex Tasks
By
–
The updated Deep Think mode outperforms Gemini 3 Pro on Humanity’s Last Exam and ARC-AGI-2 – raising the bar for how it handles complex math, science, and novel challenges.
-
Cerebras showcases nine papers at NeurIPS 2025 spanning pretraining to inference
By
–
Cerebras is showcasing nine new papers at NeurIPS 2025, spanning pretraining to inference:
CODA – orchestrate 32B models to beat 235B models Calibrated Reasoning – 1-3x token savings in best-of-n sampling
DREAM – 3.6× faster VLM inference using spec decode CompleteP – -
Chain of Debate: Beyond Chain of Thought in AI Reasoning
By
–
Here's the post I put on LinkedIn on "Chain of Debate" a while back: Chain of thought was just chapter one. Next up: Chain of Debate. When AIs started sharing their chain of thought (CoT), it gave us a window into its thinking – how it reasoned its way from A to B. But at the
-
GPT-5.1-Codex-Max for Agentic Coding Released
By
–
GPT-5.1-Codex-Max is now available via the Responses API and OpenAI Platform. "GPT‑5.1-Codex-Max is purpose-built for agentic coding. foundational reasoning model."
-
Why ChatGPT will lose the AI battle against Gemini
By
–
Why #ChatGPT will lose the AI battle against Google #Gemini? Full analysis → https://youtu.be/1mXQM3jS7nI
-
PosterCopilot: Layout Reasoning and Controllable Graphic Design Editing
By
–
PosterCopilot Toward Layout Reasoning and Controllable Editing for Professional Graphic Design