/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Thoughts on using LLMs for coding, which can often be difficult and unintuitive, and why “vibe coding” is a fantastic way to explore the capabilities of LLMs

Online discussions about using Large Language Models to help write code inevitably produce comments from developers who's experiences have been disappointing.

Simon Willison's Weblog Simon Willison

Context & Ripple Effects

This sits in a practical-use debate where builders have documented prompting pitfalls in real-world LLM applications, while broader commentary argued models should be assessed by demonstrated capabilities rather than their failures. The article reframes disappointing coding results as partly a problem of learning an unfamiliar interface and feedback loop, not simply a binary judgment on model quality.

That framing foreshadows later coverage in which coding agents were described as useful, while retaining the caution implicit in lessons about common prompting pitfalls. It matters because experimentation can reveal where an LLM is helpful before it is trusted with consequential code.

First-order effects

  • Developers are encouraged to use low-stakes exploratory coding sessions to learn a model’s strengths, failure modes, and interaction patterns before applying it to production work.
  • “Vibe coding” shifts the immediate goal from reliable task completion to capability discovery, making disappointment more actionable as feedback about task framing and verification needs.

Second-order effects

  • Teams adopting coding assistants will need workflows that preserve rapid experimentation while separating exploratory output from reviewed, maintainable code.
  • Tool vendors face pressure to make model behavior easier to inspect and steer, since usefulness depends on how well developers can supply context and evaluate generated changes.

Third-order effects

  • If exploratory use becomes a normal onboarding path, AI-assisted development may be organized around context preparation and human validation rather than one-shot code generation.
  • The durable dividing line may be between tasks where iterative feedback is cheap and reversible and tasks where errors are costly; broad adoption will depend on tools narrowing that gap.

The trend: Coding AI is moving from a promise of autonomous code generation toward workflow-native assistance that developers learn, direct, and verify through iteration.

Discussion

  • @simonwillison.net Simon Willison on bluesky
    Here's the table of contents for my lengthy new piece on how I use LLMs to help me write code simonwillison.net/2025/Mar/11/ ...  [image]
  • @dksf @dksf on x
    “vibe coding” starter guide 👇 (I've made 3 simple games already to play locally, will deploy my first one publicly soon and share here)
  • @jeyffre Jeffrey Scholz on x
    Vibecoding then vs vibecoding now. [image]
  • @vineetwts @vineetwts on x
    Vibe coding will create more illiterate programmers than college does
  • @jarrodwattsdev Jarrod Watts on x
    Average vibe coding experience: > here we go, vibe coding time. > giga prompt, docs indexed, .cursorrules. > it produces absolute slop > “ok.. NO that is not the right way to do it” > “do it this way instead”. > “DUDE NO that is not right”. > do it myself I'm not convinced lmao
  • @dennisonbertram Dennison on x
    Here's my Vibecoding stack: I plan first, separately. I workshop and idea with ChatGPT: 4, 4.5 and o3 mini are all quite good. First I do a PRD and chat back and forth about the idea.
  • @notionhq @notionhq on x
    No code vibe coding [video]
  • @alexisgauba Alexis on x
    vibe coding [image]
  • @bigboxswe @bigboxswe on x
    vibe coding is what happens when you let MBAs and ‘Product People’ near an AI slop generating text editor. we need stronger guardrails and gatekeeping around programming
  • @thekitze @thekitze on x
    bro has been vibe coding for 5 yrs
  • @din0s_ Dinos on x
    earliest record of vibecoding
  • @skooookum @skooookum on x
    so basically The President is vibe coding but with the economy
  • @jonhearty @jonhearty on x
    i thought i liked coding but after vibe coding, i'm realizing that i like the quick feedback loop of idea to product platforms like replit's v2 agent increase that feedback look by orders of magnitude the future is going to be wild and come extremely quickly