<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/v1h7lV5f7" -->

---
title: Thoughts on LLMs | daily.dev
description: A distributed systems researcher reflects on two years of writing about LLMs, compiling an index of past posts on the topic. The core recurring take: LLMs...
canonical: https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Thoughts on LLMs | daily.dev
og:description: A distributed systems researcher reflects on two years of writing about LLMs, compiling an index of past posts on the topic. The core recurring take: LLMs...
og:url: https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7
og:image: https://api.daily.dev/og/posts/v1h7lV5f7.png
og:image:alt: Thoughts on LLMs
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.

# Thoughts on LLMs

**[Metadata](https://daily.dev/sources/muratbuffalo)** · 4 min read · 7 upvotes · 2 comments

## Summary

A distributed systems researcher reflects on two years of writing about LLMs, compiling an index of past posts on the topic. The core recurring take: LLMs excel at high-throughput mediocrity, producing output that looks impressive to non-experts but merely adequate to those with domain expertise (a Gell-Mann amnesia effect). The author values LLMs for offloading mundane project work, especially helpful for ADHD-driven momentum, while insisting the real thinking, writing, and planning still happens in Emacs. A second list rounds up posts where AI intersected with the author's formal-methods and systems research work, including model checking, TLA+ workshops, and AI coding productivity studies.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://muratbuffalo.blogspot.com/2026/08/thoughts-on-llms.html>

## Community discussion

Top comments from developers on daily.dev.

**@jliter85** · 2 upvotes

> I like the way you put this. I use AI a lot, and for me the biggest advantage is keeping momentum going. I can hand off the repetitive stuff, get a starting point, or work through something I’m stuck on and then spend my time improving it and building the parts that actually need my attention. AI is a tool, and learning when to use it is just as important as learning how to use it.

**@agustinbarrientos** · 0 upvotes

> With TLA+, I'd keep the model and implementation in separate contexts. I'd compare their assumptions before treating a passing check as agreement. A human can resolve cases where both are internally consistent but describe different systems.

## Similar posts on daily.dev

- [The LLM Critics Are Right. I Use LLMs Anyway.](https://daily.dev/posts/the-llm-critics-are-right-i-use-llms-anyway--02xhbt7xl) · Hacker News · 4 upvotes · 1 comments
- [On LLMs in programming](https://daily.dev/posts/on-llms-in-programming-rmfrkf6na) · Lobsters · 1 upvotes · 0 comments
- [LLMs’ impact on science: Booming publications, stagnating quality](https://daily.dev/posts/llms-impact-on-science-booming-publications-stagnating-quality-z0ogr1wdt) · Ars Technica · 0 upvotes · 0 comments
- [Why LLMs Rock \(or: BooLLMean Logic for the Uninitiated\)](https://daily.dev/posts/why-llms-rock-or-boollmean-logic-for-the-uninitiated--66elcilfw) · Beam Bloggers Webring · 0 upvotes · 0 comments
- [Let’s talk about LLMs](https://daily.dev/posts/let-s-talk-about-llms-ibmomy8y5) · Planet Python · 1 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding), [#distributed-systems](https://daily.dev/tags/distributed-systems), [#agentic-ai](https://daily.dev/tags/agentic-ai)

[View this post on daily.dev](https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7)

```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":"Thoughts on LLMs","url":"https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7"},"datePublished":"2026-08-23T18:42:14.159Z","dateModified":"2026-09-14T07:43:53.163Z","description":"A distributed systems researcher reflects on two years of writing about LLMs, compiling an index of past posts on the topic. The core recurring take: LLMs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/011a1e11930793232fffcce3d9823b80?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/011a1e11930793232fffcce3d9823b80?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Metadata","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":"Metadata","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/90c118a936634226b4410f63cfc78371","url":"https://daily.dev/sources/muratbuffalo"},"commentCount":2,"discussionUrl":"https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":7},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"keywords":"llm,ai-coding,distributed-systems,agentic-ai","timeRequired":"PT4M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Metadata","item":"https://daily.dev/sources/muratbuffalo"},{"@type":"ListItem","position":3,"name":"Thoughts on LLMs"}]}
{"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/thoughts-on-llms-v1h7lv5f7","comment":[{"@type":"Comment","text":"I like the way you put this. I use AI a lot, and for me the biggest advantage is keeping momentum going. I can hand off the repetitive stuff, get a starting point, or work through something I’m stuck on and then spend my time improving it and building the parts that actually need my attention. AI is a tool, and learning when to use it is just as important as learning how to use it.","datePublished":"2026-08-24T01:58:23.677Z","url":"https://daily.dev/posts/v1h7lV5f7#c-3Y4oHjoSh","author":{"@type":"Person","name":"John Liter","url":"https://daily.dev/jliter85","image":"https://media.daily.dev/image/upload/s--DQ2HUrO4--/f_auto/v1785100315/avatars/avatar_yHf9cPdgTQEtokv6d8qhM?_a=BAMAMicg0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"With TLA+, I’d keep the model and implementation in separate contexts. I’d compare their assumptions before treating a passing check as agreement. A human can resolve cases where both are internally consistent but describe different systems.","datePublished":"2026-08-27T16:29:16.183Z","url":"https://daily.dev/posts/v1h7lV5f7#c-smpzzSakd","author":{"@type":"Person","name":"Agustin Barrientos","url":"https://daily.dev/agustinbarrientos","image":"https://media.daily.dev/image/upload/s--5ayxQnqn--/f_auto/v1788281802/avatars/avatar_wQYYVe5Tbj0NJ7C7qPoa8?_a=BAMAMicg0"}}]}
```

