Mostly instructing it to do things on a schedule and then it drifting further and further away from what it was instructed to do. Like it will follow instructions for a day or two and then seemingly forget what was instructed a few days prior.
LLMS
-
Use the right AI model for each task
By
–
Stop asking one AI to do everything. The frontier isn't one model. It's knowing which model to use for which job.
-
Model personality swap creates perfect planner-executor combo
By
–
The models swapped personalities this month. Opus 4.7 got more rigid and precise. GPT-5.5 got more natural and conversational. That's not a bug. That's why this combo works. One model became the perfect planner. The other became the perfect executor. Use them for what
-
Opus outlines, GPT-5.5 drafts and executes
By
–
This works beyond coding. Content strategy: use Opus to outline the argument structure. Use GPT-5.5 to draft. Research: use Opus to design the research methodology. Use GPT-5.5 to execute the analysis. Business planning: use Opus to define the framework. Use GPT-5.5 to
-
External plans boost GPT-5.5’s confidence and productivity
By
–
Step 3: Let GPT-5.5 run. It will work through the plan methodically. The key insight: GPT-5.5 is more confident when given explicit instructions from an external plan than when it generates its own. It stops second-guessing. It stops being lazy. It builds.
-
Learning with AI Agents from X’s Smartest People
By
–
And it isn't really fair criticism. I've been on many spaces defending you all against criticism.
-
Codebase analysis and rewrite planning with Claude Opus 4.7
By
–
The exact workflow: Step 1: Open Claude. Select Opus 4.7. Prompt:
"Analyze this codebase. Write a detailed rewrite plan from first principles. Include exact file structure, line limits per file, and architectural decisions. Do not write any code. Plan only." -
Opus 4.7 tight plans enable GPT-5.5 confident execution
By
–
Why this works. Opus 4.7 writes tight, contract-style plans. Exact file counts. Line limits. First-principles architecture. It thinks like a senior engineer scoping a project. GPT-5.5 reads that plan and executes with confidence. It deletes files, rewrites from scratch,
-
Opus 4.7 plus GPT-5.5 nearly doubles benchmark scores
By
–
Dan Shipper at Every tested this on their Senior Engineer Benchmark. The scores:
Opus 4.7 alone: low 30s GPT-5.5 alone: low-to-mid 40s Opus 4.7 planning + GPT-5.5 executing: 62.5 For reference, human senior engineers score 80-90. The combo nearly doubled either model's -
DeepAgents CLI Coding Harness Shines With Open Weight Models
By
–
open weight models are having a moment @masondrxy is making deepagents cli a coding harness that works amazing with open weight models what is missing? what should he add? try it out!