Claude Fable 5.2 coding edits follow prompt ownership wording
Calling the codebase the model’s led it to merge repeated code in about half of small-task tries, versus under a tenth otherwise.
Stories per day · 30 days
4 RSS
Relatedclaude2llm2ai-scientists1anthropic1artifacts1bvsr1canvas1claude-code1clinical-benchmark1coding-agents1design-science1developer-tools1enterprise-data1evaluation1fable1game-development1harness1idea-generation1
16 stories, newest first · one card per story
Stories tagged #prompting
BVSR limits task info during AI-scientist idea generation
Across five proposers and 12 tasks, limited information raised originality and later selection discarded half the candidates.
Prompting versus token probabilities tested on semantic focus
Token probabilities beat chance across sizes, while prompting sometimes wins widely in larger models.
NPC-RubricBench shows LLM cancer-care errors reverse by phase
Across 405 patients, strong diagnosis did not carry into later care, and prompt style traded quality against faithfulness.
Quick Study prompt has Claude paint a photo on canvas
The prompt asks Claude Opus 5.5 High to open a photo and repaint it with a simulated brush in a few seconds.
Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs
A knowledge-graph layer resolves imperfect enterprise prompts better than schema-only semantic matching.
How to engineer an AI harness for game development
A Calgary talk argues game LLMs need harnesses because much of a game is not code.
7
Foundations of Large Language Models
A six-chapter book covers LLM pre-training, generation, prompting, alignment, inference, and reasoning.
Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
LASEF finds English reasoning skeletons help smaller models slightly, but language choice is context-dependent.
Getting the most out of Opus 5.5 in Claude and Claude Code
Anthropic explains how to prompt, steer, and check long Claude Opus 5.5 runs in Claude and Claude Code.
A single function Jev-like wrapper for LLMs, including vision models
A developer blog shows a Jev-style logprob wrapper that scores webcam frames with text and vision LLMs.
5
Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis
A study finds graph-structured LLM reasoning lifts cybersecurity analysis accuracy by up to 12.2 points.
Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks
A 267-word specification frame cut security defects in code from five frontier models, and never made any model worse.
How to Write with an LLM
Thomas Ptacek publishes a method for LLM-assisted writing: never adopt suggested words and forbid model encouragement to preserve author voice.
3
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?
Six frontier models from OpenAI, Anthropic, xAI, and Google DeepMind converge on one imagined successor architecture when asked under a school-audience framing.
GPT-6 Astra needs leaner prompts and fewer guardrails, OpenAI recommends
OpenAI's Eric Provencher advises developers using GPT-6 Astra to shorten skill descriptions, trim AGENTS.md reading requirements, relax approval rules, and define clear completion goals.
4