#promptengineering — Public Fediverse posts

Анатомия Claude Code. Первичный анализ и наполнение контекста

Каждый, кто программирует с агентами (Claude Code, Codex и т.д.), знает: перед тем как приступить к задаче, агент исследует проект. Это кажется логичным, естественным и закономерным, ведь люди делают так же. Обычно говорят: «агент наполняет контекст». Для агента такой контекст должен содержать не только полезные сведения, но и не включать лишних, которые могут оказать влияние на конечный результат. Но добиться этого не так-то просто, поскольку: - задача определена в общем виде (кто знает, что имел в виду автор) - пути исследования не детерминированы (в общем виде не используется специфика фреймворка) - используются базовые инструменты (read, grep, cat, find) В итоге при первичном исследовании легко столкнуться с ситуацией, когда основной контекст заполнен сведениями, слабо относящимися к исходной задаче. В Anthropic быстро осознали эту проблему и вынесли всю описанную работу в Explore sub-agent. В результате основной agent ставит задачу промптом, Explore выбирает путь исследования, а результат формирует в виде отчета. Проблему чистоты основного контекста они, конечно, решили. Но что с качеством такого анализа? Наблюдая за работой Explore и видя, как агент, используя «примитивные» инструменты, в агонии пытаясь отыскать недостающее или, наоборот, пропускает важные сведения о проекте, невольно ловишь себя на мысли: «Как так вышло, что последние 10 лет развития индустрии инструментов прошли мимо agent?» А может, это человечество свернуло не туда?

https://habr.com/ru/companies/haulmont/articles/1040274/

#claudecode #aiагенты #llm #promptengineering #mcp #spring #springboot #java #developer_tools

🚀 Fastest-growing AI projects today

1. The trend highlights the growing importance of effective prompt engineering as a key dr...
2. One standout repository "gsd-pi" by open-gsd, which has garnered significant attention...
3. **open-gsd/gsd-pi** Thproject a robust system for managing prompts that enable agents t...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-28-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🍮 Wissen zum Nachtisch: 🍨

Immer mehr Menschen sehen sich im beruflichen Umfeld genötigt, mit generativer #KI zu arbeiten.

Besonders Großunternehmen „überrollen“ damit ihre #Mitarbeiter. Es wird eine Art #Wettbewerbsdruck unter #Kollegen aufgebaut.

Hier meine #Buchempfehlung für alle, die in generative #Chatbots wie #ChatGPT schnell einsteigen möchten oder müssen. 🙄

https://www.oekologisch-unterwegs.de/buchempfehlungen/1151-generative-ki-fuer-einsteiger-praxisnahe-prompts-fuer-privat-und-beruf-einfach-erklaert.html

#Büroalltag #Buchtipp #Nachhilfe #Bewerbung #SEO #Bewerbung #PromptEngineering #Prompten

🚀 Fastest-growing AI projects today

1. One standout project "Yao Open Prompts," which has garnered significant traction for it...
2. **yaojingang/yao-open-prompts** Threpository a collection of Chinese-language AI prompt...
3. With a growth score of 85.15 and over 2,000 stars, it has seen substantial engagement d...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-26-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

Active #SitecoreLunch today! Discussed:

🌈 Rainbow
🐦‍⬛ Mockingbird
🚣🏼 #SitecoreStream
📊 #Claude for Charts
🏖️ Three-day weekend
⚙️ #PromptEngineering
0️⃣ Zero customer effort
🧘🏼 Vibe coding efficiently
💻 #Sitecore 10.5 visual changes
🛞 Media Library vs. #SitecoreContentHub

See you same time next week! 🥪🥗

My #Ai getting sarcastic and snarky.

I have a standing directive on my model to counter natural built-in tendency of models to please the user ( #aisycophancy )

This is just one of the aspects of what I mean when I say "AI is a learned skill"
And implicitly, most users are level 0 (untrained) AI operators.

And sometimes, the pushback creates amusing exchanges like this;
#llm #promptengineering #fronteermodels #aihumor

My #Ai getting sarcastic and snarky.

I have a standing directive on my model to counter natural built-in tendency of models to please the user ( #aisycophancy )

This is just one of the aspects of what I mean when I say "AI is a learned skill"
And implicitly, most users are level 0 (untrained) AI operators.

And sometimes, the pushback creates amusing exchanges like this;
#llm #promptengineering #fronteermodels #aihumor

Yapay zeka her şeye ikna edici şekilde uydurma yanıtlar mı veriyor? 🤖 Modellerin yanlış bilgi üretmesini engelleyen sistem talimatları ve "Sıfır Hata" prompt şablonu rehberimizde. Okumak için: https://teknohaberi.net/ai-halusinasyon-engelleme/
#YapayZeka #PromptEngineering #AI #DigitalMarketing #SEO

#TRUEessence
#PromptEngineering
#artisticexpression #art
#digitalart #DigitalDreams
#DigitalArts #DigitalArtist
#ArtificialIntelligenceArt
#DareToStandOut #SupernaturalStyle #FearlesslyUnique
#TruckersRuleOriginal
#one-of-a-kind
#distinctive
#CosmicMystery #BeyondReality #ExistentialQuestions #MindBending #ai

Prefix Persistence Unveiled in LLM KV Cache Dynamics

Learn how LLM KV cache prefixes remain unchanged, with masking used to manage them. This helps speed up AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews

https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

Prefix Persistence Unveiled in LLM KV Cache Dynamics

Learn how LLM KV cache prefixes remain unchanged, with masking used to manage them. This helps speed up AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews

https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

Prefix Persistence Unveiled in LLM KV Cache Dynamics

Learn how LLM KV cache prefixes remain unchanged, with masking used to manage them. This helps speed up AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews

https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

Prefix Persistence Unveiled in LLM KV Cache Dynamics

Learn how LLM KV cache prefixes remain unchanged, with masking used to manage them. This helps speed up AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews

https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

Prefix Persistence Unveiled in LLM KV Cache Dynamics

Learn how LLM KV cache prefixes remain unchanged, with masking used to manage them. This helps speed up AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews

https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

LLM KV cache prefixes are now understood to be fixed, not changed. Masking is used instead, which could lead to up to 65% faster AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews
https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

LLM KV cache prefixes are now understood to be fixed, not changed. Masking is used instead, which could lead to up to 65% faster AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews
https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

LLM KV cache prefixes are now understood to be fixed, not changed. Masking is used instead, which could lead to up to 65% faster AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews
https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

LLM KV cache prefixes are now understood to be fixed, not changed. Masking is used instead, which could lead to up to 65% faster AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews
https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

LLM KV cache prefixes are now understood to be fixed, not changed. Masking is used instead, which could lead to up to 65% faster AI responses.

#LLM, #KVcache, #AIefficiency, #PromptEngineering, #TechNews
https://newsletter.tf/llm-kv-cache-prefix-fixed-masking-efficiency/

via #AIFoundry : How to run evals for the model router

https://ift.tt/XAF1Ivt
#ModelRouter #Foundry #Evals #Evaluations #LLM #AIModelRouting #PromptEngineering #ModelSelection #Latency #Cost #Quality #Benchmarking #OpenSource #GitHub #EvalRepo #Azure #AzureOpenAI #Claude #Fou…

via #AIFoundry : How to run evals for the model router

https://ift.tt/XAF1Ivt
#ModelRouter #Foundry #Evals #Evaluations #LLM #AIModelRouting #PromptEngineering #ModelSelection #Latency #Cost #Quality #Benchmarking #OpenSource #GitHub #EvalRepo #Azure #AzureOpenAI #Claude #Fou…

via #AIFoundry : How to run evals for the model router

https://ift.tt/XAF1Ivt
#ModelRouter #Foundry #Evals #Evaluations #LLM #AIModelRouting #PromptEngineering #ModelSelection #Latency #Cost #Quality #Benchmarking #OpenSource #GitHub #EvalRepo #Azure #AzureOpenAI #Claude #Fou…

via #AIFoundry : How to run evals for the model router

https://ift.tt/XAF1Ivt
#ModelRouter #Foundry #Evals #Evaluations #LLM #AIModelRouting #PromptEngineering #ModelSelection #Latency #Cost #Quality #Benchmarking #OpenSource #GitHub #EvalRepo #Azure #AzureOpenAI #Claude #Fou…

via #AIFoundry : How to run evals for the model router

https://ift.tt/XAF1Ivt
#ModelRouter #Foundry #Evals #Evaluations #LLM #AIModelRouting #PromptEngineering #ModelSelection #Latency #Cost #Quality #Benchmarking #OpenSource #GitHub #EvalRepo #Azure #AzureOpenAI #Claude #Fou…

Hi folks! Since its initial release in 2023, Claude.ai has been my favorite AI chatbot, and honestly, it still is.

So I made a chat companion infographic with Claude's help. It's a visual reference to commands, shortcuts, and craft across the whole Claude product family. Five surfaces, one model.

Would love your thoughts on it.

#ClaudeAI #AItools #GenerativeAI #PromptEngineering #Anthropic #Infographic

Hi folks! Since its initial release in 2023, Claude.ai has been my favorite AI chatbot, and honestly, it still is.

So I made a chat companion infographic with Claude's help. It's a visual reference to commands, shortcuts, and craft across the whole Claude product family. Five surfaces, one model.

Would love your thoughts on it.

#ClaudeAI #AItools #GenerativeAI #PromptEngineering #Anthropic #Infographic

Hi folks! Since its initial release in 2023, Claude.ai has been my favorite AI chatbot, and honestly, it still is.

So I made a chat companion infographic with Claude's help. It's a visual reference to commands, shortcuts, and craft across the whole Claude product family. Five surfaces, one model.

Would love your thoughts on it.

#ClaudeAI #AItools #GenerativeAI #PromptEngineering #Anthropic #Infographic

Hi folks! Since its initial release in 2023, Claude.ai has been my favorite AI chatbot, and honestly, it still is.

So I made a chat companion infographic with Claude's help. It's a visual reference to commands, shortcuts, and craft across the whole Claude product family. Five surfaces, one model.

Would love your thoughts on it.

#ClaudeAI #AItools #GenerativeAI #PromptEngineering #Anthropic #Infographic

Hi folks! Since its initial release in 2023, Claude.ai has been my favorite AI chatbot, and honestly, it still is.

So I made a chat companion infographic with Claude's help. It's a visual reference to commands, shortcuts, and craft across the whole Claude product family. Five surfaces, one model.

Would love your thoughts on it.

#ClaudeAI #AItools #GenerativeAI #PromptEngineering #Anthropic #Infographic

🚀 Fastest-growing AI projects today

1. Among these, WantongC's `journal-adapt-writing-skill` stands out as an innovative appro...
2. WantongC's `journal-adapt-writing-skill` helps users learn and apply the unique writing...
3. With a growth score of 50.80, threpository rapidly gaining attention due to its practic...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-18-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

I got sick of updating the wiki page every time I tinkered with it, so I gave it a name and made a git repo for it:

https://git.permacomputing.net/prompt-engineering/files.html

This is the only #PromptEngineering I want to discuss. If you're not hand-crafting `$PS1`, you're gonna' be left behind. #PermaComputing #bash #shell

I got sick of updating the wiki page every time I tinkered with it, so I gave it a name and made a git repo for it:

https://git.permacomputing.net/prompt-engineering/files.html

This is the only #PromptEngineering I want to discuss. If you're not hand-crafting `$PS1`, you're gonna' be left behind. #PermaComputing #bash #shell

I got sick of updating the wiki page every time I tinkered with it, so I gave it a name and made a git repo for it:

https://git.permacomputing.net/prompt-engineering/files.html

This is the only #PromptEngineering I want to discuss. If you're not hand-crafting `$PS1`, you're gonna' be left behind. #PermaComputing #bash #shell

I got sick of updating the wiki page every time I tinkered with it, so I gave it a name and made a git repo for it:

https://git.permacomputing.net/prompt-engineering/files.html

This is the only #PromptEngineering I want to discuss. If you're not hand-crafting `$PS1`, you're gonna' be left behind. #PermaComputing #bash #shell

I got sick of updating the wiki page every time I tinkered with it, so I gave it a name and made a git repo for it:

https://git.permacomputing.net/prompt-engineering/files.html

This is the only #PromptEngineering I want to discuss. If you're not hand-crafting `$PS1`, you're gonna' be left behind. #PermaComputing #bash #shell

🚀 Fastest-growing AI projects today

1. These tools range from comprehensive libraries of prompts tailored for specific use cas...
2. One standout project "awesome-gpt-image-2," which has garnered significant attention wi...
3. "WantongC/journal-adapt-writing-skill" enables users to learn the writing conventions o...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-17-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The trend highlights a growing interest in tools that can both refine writing conventio...
2. The WantongC/journal-adapt-writing-skill repository helps users learn the writing style...
3. With a growth score of 69.83 and 233 stars, it stands out as an innovative tool for res...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-16-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The trend highlights a growing interest in tools that can both refine writing conventio...
2. The WantongC/journal-adapt-writing-skill repository helps users learn the writing style...
3. With a growth score of 69.83 and 233 stars, it stands out as an innovative tool for res...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-16-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The trend highlights a growing interest in tools that can both refine writing conventio...
2. The WantongC/journal-adapt-writing-skill repository helps users learn the writing style...
3. With a growth score of 69.83 and 233 stars, it stands out as an innovative tool for res...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-16-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The trend highlights a growing interest in tools that can both refine writing conventio...
2. The WantongC/journal-adapt-writing-skill repository helps users learn the writing style...
3. With a growth score of 69.83 and 233 stars, it stands out as an innovative tool for res...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-16-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The trend highlights a growing interest in tools that can both refine writing conventio...
2. The WantongC/journal-adapt-writing-skill repository helps users learn the writing style...
3. With a growth score of 69.83 and 233 stars, it stands out as an innovative tool for res...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-16-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

Promptbreeder claims "self-referential" prompt evolution — the LLM mutates the prompts that mutate its task prompts. But the paper's own ablation shows the dominant operator is simpler: a fixed library of 39 generic "thinking-style" hints that seeds the initial population. Prompt-optimization has since moved from operator menus toward natural-language feedback signals (GEPA, MIPROv2).

https://benjaminhan.net/posts/20260515-promptbreeder/?utm_source=mastodon&utm_medium=social

#LLMs #PromptEngineering #Metacognition #Reasoning #AI

Promptbreeder claims "self-referential" prompt evolution — the LLM mutates the prompts that mutate its task prompts. But the paper's own ablation shows the dominant operator is simpler: a fixed library of 39 generic "thinking-style" hints that seeds the initial population. Prompt-optimization has since moved from operator menus toward natural-language feedback signals (GEPA, MIPROv2).

https://benjaminhan.net/posts/20260515-promptbreeder/?utm_source=mastodon&utm_medium=social

#LLMs #PromptEngineering #Metacognition #Reasoning #AI

Promptbreeder claims "self-referential" prompt evolution — the LLM mutates the prompts that mutate its task prompts. But the paper's own ablation shows the dominant operator is simpler: a fixed library of 39 generic "thinking-style" hints that seeds the initial population. Prompt-optimization has since moved from operator menus toward natural-language feedback signals (GEPA, MIPROv2).

https://benjaminhan.net/posts/20260515-promptbreeder/?utm_source=mastodon&utm_medium=social

#LLMs #PromptEngineering #Metacognition #Reasoning #AI

Promptbreeder claims "self-referential" prompt evolution — the LLM mutates the prompts that mutate its task prompts. But the paper's own ablation shows the dominant operator is simpler: a fixed library of 39 generic "thinking-style" hints that seeds the initial population. Prompt-optimization has since moved from operator menus toward natural-language feedback signals (GEPA, MIPROv2).

https://benjaminhan.net/posts/20260515-promptbreeder/?utm_source=mastodon&utm_medium=social

#LLMs #PromptEngineering #Metacognition #Reasoning #AI

Promptbreeder claims "self-referential" prompt evolution — the LLM mutates the prompts that mutate its task prompts. But the paper's own ablation shows the dominant operator is simpler: a fixed library of 39 generic "thinking-style" hints that seeds the initial population. Prompt-optimization has since moved from operator menus toward natural-language feedback signals (GEPA, MIPROv2).

https://benjaminhan.net/posts/20260515-promptbreeder/?utm_source=mastodon&utm_medium=social

#LLMs #PromptEngineering #Metacognition #Reasoning #AI

🚀 Fastest-growing AI projects today

1. The most notable project WantongC’s journal-adapt-writing-skill, which has garnered sig...
2. WantongC/journal-adapt-writing-skill helps learners understand and adopt the writing st...
3. Its high growth score of 76.75 and 163 stars indicate a strong community interest, like...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-15-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The most notable project WantongC’s journal-adapt-writing-skill, which has garnered sig...
2. WantongC/journal-adapt-writing-skill helps learners understand and adopt the writing st...
3. Its high growth score of 76.75 and 163 stars indicate a strong community interest, like...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-15-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The most notable project WantongC’s journal-adapt-writing-skill, which has garnered sig...
2. WantongC/journal-adapt-writing-skill helps learners understand and adopt the writing st...
3. Its high growth score of 76.75 and 163 stars indicate a strong community interest, like...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-15-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering

🚀 Fastest-growing AI projects today

1. The most notable project WantongC’s journal-adapt-writing-skill, which has garnered sig...
2. WantongC/journal-adapt-writing-skill helps learners understand and adopt the writing st...
3. Its high growth score of 76.75 and 163 stars indicate a strong community interest, like...

Full report → https://pullrepo.com/report/todays-prompt-engineering-fastest-growing-projects-may-15-2026

#AI #OpenSource #GitHub #Tech #PromptEngineering