I Built the Same Agent in LangGraph, CrewAI, and AutoGen — Microsoft Quit the 56K-Star Favorite
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. I Built the Same Agent in LangGraph, CrewAI, and AutoGen — Microsoft Quit the 56K-Star Favorite I spent a weekend building the exact same two-agent pipeline three times — once …
Sakana Trained One AI to Command GPT-5.5, Opus, and Gemini — It Cracked 73.7 Where They Stalled at 69
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Sakana Trained One AI to Command GPT-5.5, Opus, and Gemini — It Cracked 73.7 Where They Stalled at 69 Two days ago a Tokyo lab shipped a model that scored …
The Best Engineers Stopped Writing Prompts: The 4 Layers That Replaced Prompt Engineering
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. The Best Engineers Stopped Writing Prompts: The 4 Layers That Replaced Prompt Engineering Boris Cherny built Claude Code. In June 2026 he said the quiet part out loud: “I don’t …
A Startup Says It Cracked AI’s Decade-Old Math Limit — Its LLM Read 12M Tokens for $8
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. A Startup Says It Cracked AI's Decade-Old Math Limit — Its LLM Read 12M Tokens for $8 A Miami startup says it ran a long-context job that costs about $2,600 …
Cohere’s 30B Coding Agent Beats Models 4x Its Size on One H100 — and It Shouldn’t
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Cohere's 30B Coding Agent Beats Models 4x Its Size on One H100 — and It Shouldn't A 30-billion-parameter model with only 3 billion active parameters has no business landing 0.6 …
I Tested GLM-5.2 vs GPT-5.5 vs DeepSeek V4 on 18 Coding Tasks — The Open One Won at One-Sixth the Cost
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. I Tested GLM-5.2 vs GPT-5.5 vs DeepSeek V4 on 18 Coding Tasks — The Open One Won at One-Sixth the Cost I gave the same 18 coding tasks to three …
I Trained a Markdown File to Boost GPT-5.5 by 23 Points — It Shouldn’t Work
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. I Trained a Markdown File to Boost GPT-5.5 by 23 Points — It Shouldn’t Work I did not fine-tune anything. I did not touch a single weight. I ran a …
OpenAI Bought a Whole Company So Codex Could Code 25 Hours After You Close Your Laptop
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Why an agent dies when you close the laptop OpenAI documented a single Codex run that went for about 25 hours uninterrupted, burned roughly 13 million tokens, and produced around …
I Served the Same Model on vLLM, SGLang, and TensorRT-LLM — the Default Gives Up 29%
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. I Served the Same Model on vLLM, SGLang, and TensorRT-LLM — the Default Gives Up 29% I ran the exact same Llama on three inference engines this week, and the …
I Gave Qwen3.7-Plus a Screenshot and It Found the Exact Pixel to Click for $0.40
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. I Gave Qwen3.7-Plus a Screenshot and It Found the Exact Pixel to Click for $0.40 I uploaded a messy AWS console screenshot and asked one question: which pixel do I …
Moonshot Cracked Claude Code’s Playbook with an MIT Terminal Agent and a $0.60 Model
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Why this matters right now A Chinese lab just shipped a terminal coding agent that does almost everything Claude Code does, released the entire thing under the MIT license, and …
Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn't Be This Good A 26-billion-parameter model has no business …
I Deleted 95% of My AI Agent’s Skills and Accuracy Jumped From 77% to 97%
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. How an “agent skill” actually is A DX engineer at WorkOS named Nick Nisi did something that sounds like sabotage. He took a 10,000-line library of auto-generated “skills” he had …
The Real Bottleneck for AI Agents Isn’t Reasoning — It’s the Browser
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. The Real Bottleneck for AI Agents Isn’t Reasoning — It’s the Browser Most “AI agent” demos die at the same place: the live web. The model writes flawless code. It …
Claude Code’s Creator Stopped Prompting Claude — He Writes Loops and Merges 150 PRs a Day From His Phone
Author(s): Chew Loong Nian – AI ENGINEER Originally published on Towards AI. Claude Code's Creator Stopped Prompting Claude — He Writes Loops and Merges 150 PRs a Day From His Phone Boris Cherny, the person who created Claude Code, hasn’t hand-written a …
Recent Posts
