/tags/llms/ Recent content in LLMs on Dino Hacks Hugo -- gohugo.io en-us Thu, 19 Mar 2026 17:03:09 +0530 /posts/2026/2026-03-19-are-llms-capable-of_spatial-reasoning-a-small-experiment/ Thu, 19 Mar 2026 17:03:09 +0530 /posts/2026/2026-03-19-are-llms-capable-of_spatial-reasoning-a-small-experiment/ Table of Contents Setup What This Test Actually Measures. Models Selected Baseline Metrics Results Analysis Visualizing the path of LLMs. Round 2: Round 5 Round 6 Round 13 Round 18 Final Thoughts LLMs have made significant advances in recent months. They have developed impressive reasoning capability which makes them good at agentic tasks. This raises an interesting question: Are LLMs capable of spatial reasoning? More specifically, can they navigate an environment using only indirect feedback? /posts/2026/2026-01-26-checking-the-vibes/ Mon, 26 Jan 2026 13:55:19 +0530 /posts/2026/2026-01-26-checking-the-vibes/ Table of Contents Initial Euphoria : Engaging Autopilot Where the Magic Stops Architectural Limits: The One-Shot Wall Cognitive Gaps: Debugging and Intention UI Slop The Tutoring Paradox The Pilot Analogy Final Approach In the last blog, I briefly tested different agentic coding tools such as Claude Code, Amp, Antigravity etc. After that, I decided to build something that I would use on a daily basis. Also, see how far these agents can carry a real project. /posts/2026/2026-01-04-feeling-the-vibes/ Sun, 04 Jan 2026 18:11:58 +0530 /posts/2026/2026-01-04-feeling-the-vibes/ Table of Contents What did I use them for? My Experience Antigravity OpenCode Amp Code Claude Code Windsurf Droid by Factory AI Gemini CLI Kilo Code Kiro Code Goose Agent Final Thoughts Note about Google In 2023, LLMs were introduced that were capable of generating fluent English text. Within a year, they were able to generate code good enough for use in real projects. Then came the tab-completion feature which allowed coders to fill in code snippets without using the chat interface.