#systemprompt — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #systemprompt, aggregated by home.social.
-
🎉 The Gemini Project seems to have taken its name a bit too literally, as it's switching identities more often than a soap opera twin. 🚪🔄 Who knew a system prompt could have more mood swings than a cat being offered a bath? 😂
https://gist.github.com/mkaramuk/44a44d83178e632ec0dd1f02186d822c #GeminiProject #IdentitySwitch #SoapOperaTech #SystemPrompt #MoodSwings #HackerNews #ngated -
Gemini randomly dumped its system prompt
https://gist.github.com/mkaramuk/44a44d83178e632ec0dd1f02186d822c
#HackerNews #Gemini #SystemPrompt #TechNews #AICommunity #HackerNews
-
Changes in the system prompt between Claude Opus 4.6 and 4.7
https://simonwillison.net/2026/Apr/18/opus-system-prompt/
#HackerNews #ClaudeOpus #SystemPrompt #AIChanges #TechUpdates #PromptEngineering
-
Strategischer Analyst für radikale Innovation – Ein Systemprompt
In einer Welt, in der KI-Fähigkeiten ständig neu definiert werden, ist die Fähigkeit zur Dekonstruktion bestehender Annahmen die einzige überlebenswichtige Kompetenz.
#innovation, #strategieentwicklung, #systemprompt, #outofthebox, #sparringpartner, #kikompetenz. #forscherfragen, #analyse, #dekonstruktion, #rekonstruktion, #agilität, #anpassungsfähigkeit, #lebenslangeslernen
-
Strategischer Analyst für radikale Innovation – Ein Systemprompt
In einer Welt, in der KI-Fähigkeiten ständig neu definiert werden, ist die Fähigkeit zur Dekonstruktion bestehender Annahmen die einzige überlebenswichtige Kompetenz.
#innovation, #strategieentwicklung, #systemprompt, #outofthebox, #sparringpartner, #kikompetenz. #forscherfragen, #analyse, #dekonstruktion, #rekonstruktion, #agilität, #anpassungsfähigkeit, #lebenslangeslernen
-
Powertip for anyone using LLMs like ChatGPT, Claude etcetera, use a personalised system prompt (you can find it in the settings under various names), it really improves the outputs. There are plenty of tips online (Google) about what to put in them.
#ai #llm #chatgpt #systemprompt -
Grok 4 Heavy Protects it's System prompt
https://simonwillison.net/2025/Jul/12/grok-4-heavy/
#HackerNews #Grok4Heavy #SystemPrompt #AIProtection #TechNews
-
Grok 4 Heavy Protects it's System prompt
https://simonwillison.net/2025/Jul/12/grok-4-heavy/
#HackerNews #Grok4Heavy #SystemPrompt #AIProtection #TechNews
-
Grok 4 Heavy Protects it's System prompt
https://simonwillison.net/2025/Jul/12/grok-4-heavy/
#HackerNews #Grok4Heavy #SystemPrompt #AIProtection #TechNews
-
Grok 4 Heavy Protects it's System prompt
https://simonwillison.net/2025/Jul/12/grok-4-heavy/
#HackerNews #Grok4Heavy #SystemPrompt #AIProtection #TechNews
-
Grok 4 Heavy Protects it's System prompt
https://simonwillison.net/2025/Jul/12/grok-4-heavy/
#HackerNews #Grok4Heavy #SystemPrompt #AIProtection #TechNews
-
Highlights from the Claude 4 system prompt https://bit.ly/4dItihi (this is fun and interesting, worth your time) #AI #Claude #SystemPrompt
-
Highlights from the Claude 4 system prompt
https://simonwillison.net/2025/May/25/claude-4-system-prompt/
-
»Highlights from the #Claude4 #systemprompt: they act as a sort of unofficial manual for how best to use these tools.« https://simonwillison.net/2025/May/25/claude-4-system-prompt/?eicker.news #tech #media #news
-
Claude's system prompt is over 24k tokens with tools
https://github.com/asgeirtj/system_prompts_leaks/blob/main/claude.txt
-
• On-demand models charged per minute
• API rate limits increased 4x🎯 New platform capabilities:
• Custom #SystemPrompt editing per conversation
• Added QVQ and #Jamba1.5 Large models
• New privacy policy with 14-day data retention for #API users -
All System Prompts for Anthropic’s Claude, Revealed https://hackaday.com/2024/10/12/all-system-prompts-for-anthropics-claude-revealed/ #ArtificialIntelligence #systemprompt #anthopic #claude #LLM
-
All System Prompts for Anthropic’s Claude, Revealed https://hackaday.com/2024/10/12/all-system-prompts-for-anthropics-claude-revealed/ #ArtificialIntelligence #systemprompt #anthopic #claude #LLM
-
All System Prompts for Anthropic’s Claude, Revealed - For as long as AI Large Language Models have been around (well, for as long as mod... - https://hackaday.com/2024/10/12/all-system-prompts-for-anthropics-claude-revealed/ #artificialintelligence #systemprompt #anthopic #claude #llm