Willison flags LLM tics, Forrester finds 88% of agent pilots fail, Quixote v3.8
Every URL the pipeline pulled into ranking for this issue — primary sources plus the supporting and contradicting findings each Researcher returned. Inline citations in the issue point back here.
Sources
LLM cliché highlighter simonwillison.net
Tool: LLM cliché highlighter I got frustrated reading yet another article that was crammed with the clichés of LLM-generated writing - “no fluff, no filler, no jargon” type stuff - so I had Fable 5 vibe code up this app for highlighting ten common patterns that show up in that sort of writing. Tags: tools , ai , generative-ai , llms
5 Trends That Defined AI Engineering at World’s Fair 2026 latent.space
At this year’s AIE World’s Fair, AI engineering entered a new phase: building systems around agents, rather than just building with agents.
nascheme/quixote simonwillison.net
nascheme/quixote A certain vintage if Python web nerd might be delighted to learn that the most recent commit to the Quixote web framework was six hours ago . The oldest commit in that repo is from 21 years ago, and that was the initial import of Quixote 2.4 from Subversion into Git. Tags: computer-history , python , web-frameworks
References
PromptMetrics — ‘AI Benchmarks vs Remote Labor Index’ promptmetrics.dev
Frontier models often exceed 90% on academic benchmarks like MMLU, [but] successfully complete less than 4% of real-world freelance tasks found on platforms like Upwork.
Komal Parmar, Medium — ‘The Hidden Problem with Multi-Agent Systems’ medium.com
MAST (Multi-Agent System Failure Taxonomy) found that these architectures fail between 41% and 86% of the time due to coordination breakdowns and context drift… 70% of tasks currently assigned to multi-agent swarms could be handled more reliably by a single agent.
Forrester — ‘The State of Agentic AI in 2026’ forrester.com
Roughly 88% of agentic AI pilots fail to reach full deployment… IT leaders’ self-assessment of their AI readiness has dropped from 40% to 23% in just six months.
GoPubby — ‘The Model Stopped Being the Hard Part’ (AIEWF 2026 review) ai.gopubby.com
AI now accounts for 27.6% of merged pull requests, [but] only approximately 48% of that code is explicitly reviewed by humans before reaching production.
AI Insiders — recap of Dex Horthy (HumanLayer) keynote aiinsiders.net
The hype is outrunning the discipline… teams are attempting to step up an abstraction level to autonomous agents before the underlying discipline has matured enough to support them.
Hacker News discussion (item 48312377) news.ycombinator.com
A widely discussed ‘grumpy screed’ compared modern AI-assisted development to CNC machining: while it is faster, the business ‘can no longer afford the craftsmanship’ of manual coding… some contributors argued for a distinction between ‘AI Engineers’ who architect systems and ‘Agentic Engineers’ who primarily use AI tools.
The Newcomer — ‘Delve and 12 other words that show…’ thenewcomerspod.com
In scientific papers, ‘delve’ jumped from fewer than 2,000 annual instances in 2022 to nearly 18,000 by early 2024
BusinessDay NG — ‘Online uproar over Nigerian English flagged as ChatGPT-ish’ businessday.ng
Nigerian writers and those educated in British-colonial systems have pointed out that ‘delve’ and similar formal terms are staples of their everyday professional vocabulary
UCLA HumTech — ‘The Imperfection of AI Detection Tools’ humtech.ucla.edu
detectors flagged over 61% of human-written TOEFL essays as AI-generated
Will Francis — ‘How to stop Claude writing like an AI’ willfrancis.com
‘unsloping’ has become a popular prompt engineering technique, where users explicitly command models to avoid these specific list patterns and rhetorical pivots
GitHub — pertrai1/ai-writing-detector github.com
Popular phrase lists now target over 500 ‘AI-tells,’ including words like delve, navigate, robust, tapestry, testament, and transformative
Matthew Vollmer Substack — ‘I asked the machine to tell on itself’ matthewvollmer.substack.com
‘It’s not just about [specific thing], it’s about [vague, grander concept]’ … mimic the shape of a significant insight while often replacing a concrete detail with a corporate cliché
Linux Journal — ‘Quixote: a Python-Centric Web Application Framework’ linuxjournal.com
Quixote was developed at MEMS Exchange to manage a complex, web-driven network of semiconductor fabrication sites… the team found Zope excessively complex and overly focused on the separation of ‘web designers’ from ‘web developers’.
BuiltWith — Very-High-Traffic Python sites trends.builtwith.com
Douban maintained its own fork (douban-quixote) and used it for critical internal infrastructure including its CODE collaboration platform; LWN.net has relied on Quixote for over two decades.
Simon Willison — Python tag archive (context on ‘vibe coding’ framing) simonwillison.net
Commenters used ‘Don Quixote’ as a metaphor for the idealistic but potentially delusional reliance on AI agents that can ‘tilt at windmills’… contrasting Quixote’s 21-year stability with rapidly abandoned AI projects.
