<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/artificial-adventures-bjp6wu9hd" -->

---
title: Artificial adventures | daily.dev
description: A developer shares a grounded, personal account of experimenting with AI coding tools including Claude Code, Codex, and various frontier models. The most...
canonical: https://daily.dev/posts/artificial-adventures-bjp6wu9hd
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Artificial adventures | daily.dev
og:description: A developer shares a grounded, personal account of experimenting with AI coding tools including Claude Code, Codex, and various frontier models. The most...
og:url: https://daily.dev/posts/artificial-adventures-bjp6wu9hd
og:image: https://api.daily.dev/og/posts/bJP6WU9Hd.png
og:image:alt: Artificial adventures
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Artificial adventures

**[Jamie Brandon](https://daily.dev/sources/jamiebrandon)** · 14 min read · 0 upvotes · 0 comments

## Summary

A developer shares a grounded, personal account of experimenting with AI coding tools including Claude Code, Codex, and various frontier models. The most consistent value came from code review (catching real bugs like double-frees) and mechanical refactoring tasks. Writing code collaboratively was frustrating due to poor AI judgment, scope creep, and difficulty reviewing AI-generated changes. Autonomous code generation for non-trivial tasks largely failed. The author also notes AI tools work well for one-off scripts and search tasks where answers are verifiable. Key observations: frontier models (Opus, GPT-5) are noticeably better than cheaper alternatives; AI safety training is easily bypassed; brainstorming suggestions are uniformly banal; and current agentic harnesses feel poorly built. The author is cautiously optimistic that better tooling and practices will improve outcomes even without smarter models.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.scattered-thoughts.net/writing/artificial-adventures>

## Similar posts on daily.dev

- [On AI](https://daily.dev/posts/on-ai-y4nttoreo) · openmymind · 0 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding), [#code-review](https://daily.dev/tags/code-review)

[View this post on daily.dev](https://daily.dev/posts/artificial-adventures-bjp6wu9hd)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Artificial adventures","url":"https://daily.dev/posts/artificial-adventures-bjp6wu9hd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/artificial-adventures-bjp6wu9hd"},"datePublished":"2026-07-02T01:08:32.490Z","dateModified":"2026-07-02T01:08:56.533Z","description":"A developer shares a grounded, personal account of experimenting with AI coding tools including Claude Code, Codex, and various frontier models. The most...","image":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","thumbnailUrl":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","isAccessibleForFree":true,"articleSection":"Jamie Brandon","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Jamie Brandon","logo":"https://media.daily.dev/image/upload/s--lWYKZ6-3--/f_auto/v1721999373/logos/jamiebrandon","url":"https://daily.dev/sources/jamiebrandon"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/artificial-adventures-bjp6wu9hd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-coding,code-review","timeRequired":"PT14M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Jamie Brandon","item":"https://daily.dev/sources/jamiebrandon"},{"@type":"ListItem","position":3,"name":"Artificial adventures"}]}
```

