links.lmorchard.com - #claude

l3a0/claude-plugins: l3a0's Claude Code plugin marketplace — kindle-highlights: verbatim Kindle highlight extraction with truncation recovery

Wed, 26 Aug 2026 00:29:41 +0000

l3a0's Claude Code plugin marketplace — kindle-highlights: verbatim Kindle highlight extraction with truncation recovery

Tags: #ai #claude #kindle #skills

RIP Claude – Rands in Repose

Tue, 25 Aug 2026 18:16:58 +0000

As a writer, no sweat, right? I write my own content. I bang on my own keys. Here’s the issue. Each of the following actions watermarks text: Synthesis Proofreading Translation Summarization Critique1 And most infuriating, the entire burden of their unannounced rollout is on me, and none of it is on them.

Tags: #ai #claude #llms #watermarking #writing

danyuchn/asd-ste100-skill: ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent-facing English.

Tue, 18 Aug 2026 16:47:04 +0000

ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent-facing English.

Tags: #agents #ai #claude #llms #skills

How Claude's text watermarking works \ Anthropic

Sat, 15 Aug 2026 02:19:36 +0000

Future Claude models will generate text that contains a watermark. This is a way of determining the likelihood that Claude was involved in writing the text, and we, along with several other major AI providers, are implementing this change to comply with the EU AI Act.

Tags: #ai #claude #llms #writing

Mea Culpa - Dark Hours — Terry Godier

Tue, 11 Aug 2026 15:32:30 +0000

About an hour later, once it became clear to me that the web app I had launched using Claude was strikingly similar to his open source project, even reproducing a bug he had later fixed, it was clear that there wasn’t anything to do except to redirect the domain directly to him and kill any plans I had to launch an iOS app for the project.

Tags: #agents #ai #claude #llms

If Claude Fable stops helping you, you'll never know — Jonathon Ready

Fri, 12 Jun 2026 16:48:43 +0000

That creates a real supply chain risk for businesses. If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in. Anthropic has explicitly chosen not to tell users when this is happening.

Tags: #ai #anthropic #claude #llms

My favorite adversarial review prompt — Massively Parallel Procrastination

Mon, 25 May 2026 03:32:55 +0000

Look at this again with fresh eyes. The phrase "fresh eyes" is kind of magic. You'll usually get startlingly good results with just that one sentence.

Tags: #agents #ai #claude #llms

claude-json-to-markdown · PyPI

Wed, 06 May 2026 12:38:46 +0000

A command-line tool that converts Anthropic Claude conversation exports to Markdown files.

Tags: #claude #markdown #python #tools

Emotion Concepts and their Function in a Large Language Model

Thu, 30 Apr 2026 22:01:03 +0000

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance with that emotion’s relevance to processing the present context and predicting upcoming text. Our key finding is that these representations causally influence the LLM’s outputs, including Claude’s preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy. We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts. Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model’s behavior.

Tags: #ai #claude #codegen #cogsci #emotions #llms

Emotion concepts and their function in a large language model \ Anthropic

Thu, 30 Apr 2026 21:58:24 +0000

All modern language models sometimes act like they have emotions. They may say they’re happy to help you, or sorry when they make a mistake. Sometimes they even appear to become frustrated or anxious when struggling with tasks. What’s behind these behaviors? The way modern AI models are trained pushes them to act like a character with human-like characteristics. In addition, these models are known to develop rich and generalizable internal representations of abstract concepts underlying their actions. It may then be natural for them to develop internal machinery that emulates aspects of human psychology, like emotions. If so, this could have profound implications for how we build AI systems and ensure they behave reliably.

Tags: #ai #claude #codegen #llms #models

System Prompts - Claude API Docs

Sat, 25 Apr 2026 17:52:07 +0000

Claude's web interface (claude.ai) and mobile apps use a system prompt to provide up-to-date information, such as the current date, to Claude at the start of every conversation. The system prompt also encourages certain behaviors, such as always providing code snippets in Markdown. This prompt is periodically updated to improve Claude's responses. These system prompt updates do not apply to the Claude API. Updates between versions are bolded.

Tags: #agents #claude #llms

I don't want a screenshot of your Claude conversation - daverupert.com

Thu, 23 Apr 2026 16:29:18 +0000

Awhile back Hidde De Vries identified a pain point around LLM-usage in standards work which leads to something I call an asymmetry of thought. In a conversation where one person is a domain expert and one person is copy-pasting ChatGPT responses, it creates an imbalance of effort in the discussion. A second-hand burdening, like Brandolini’s Law, where debunking inaccuracies and subtly-wrongs takes more effort than creating the inaccuracies. We are, in effect, taxing experts to do quality assurance on the model’s responses. When that work is unpaid I believe this is immoral… or at least it’s a breach in social etiquette.

Tags: #agents #ai #claude #llms #work

matanshavit/qrspi: QRSPI — 8-phase workflow for Claude Code: Question, Research, Structure, Plan, Implement

Sun, 19 Apr 2026 19:28:06 +0000

Question, Research, Structure, Plan, Implement — an 8-phase workflow for Claude Code that breaks complex coding tasks into focused prompts with clear artifacts between each step.

Tags: #ai #claude #codegen #llms

Push events into a running session with channels - Claude Code Docs

Fri, 27 Mar 2026 19:10:55 +0000

Use channels to push messages, alerts, and webhooks into your Claude Code session from an MCP server. Forward CI results, chat messages, and monitoring events so Claude can react while you’re away.

Tags: #agents #ai #claude #codegen

Schedule tasks on the web - Claude Code Docs

Fri, 27 Mar 2026 19:10:15 +0000

A scheduled task runs a prompt on a recurring cadence using Anthropic-managed infrastructure. Tasks keep working even when your computer is off.

Tags: #agents #ai #claude