#llmtooluse - Mastodon Uno Social - Italia

Ricerche recenti

Opzioni di ricerca

Disponibile solo dopo aver effettuato l'accesso.

2 post2 partecipanti0 post oggi

LLMs @LLMs@activitypub.awakari.com

Introducing web search on the Anthropic API Introducing web search on the Anthropic API Anthropic...

https://simonwillison.net/2025/May/7/anthropic-api-search/#atom-everything

#anthropic #generative-ai #llm-tool-use #search #ai #llms #claude

Result Details

Simon Willison’s WeblogIntroducing web search on the Anthropic APIAnthropic's [web search](https://simonwillison.net/2025/Mar/20/claude-can-now-search-the-web/) (presumably still [powered by Brave](https://simonwillison.net/2025/Mar/21/anthropic-use-brave/)) is now also available through their API, in the shape of a new [web search tool](https://docs.anthropic.com/en/docs/build-with-claude/tool-use/web-search-tool) called `web_search_20250305`. You can specify a …

#generativeAI #llmtooluse

LLMs @LLMs@activitypub.awakari.com

Introducing web search on the Anthropic API Introducing web search on the Anthropic API Anthropic...

https://simonwillison.net/2025/May/7/anthropic-api-search/#atom-everything

#anthropic #generative-ai #llm-tool-use #search #ai #llms

Result Details

Simon Willison’s WeblogIntroducing web search on the Anthropic APIAnthropic's [web search](https://simonwillison.net/2025/Mar/20/claude-can-now-search-the-web/) (presumably still [powered by Brave](https://simonwillison.net/2025/Mar/21/anthropic-use-brave/)) is now also available through their API, in the shape of a new [web search tool](https://docs.anthropic.com/en/docs/build-with-claude/tool-use/web-search-tool) called `web_search_20250305`. You can specify a …

#generativeAI #llmtooluse

LLMs @LLMs@activitypub.awakari.com

Claude feature drop It's not in their release notes yet but Anthropic pushed some big new fea...

https://simonwillison.net/2025/May/2/claude-search/#atom-everything

#alex-albert #anthropic #claude #llm-tool-use #deep-research #ai #llms #generative-ai

Result Details

Simon Willison’s WeblogNote on 2nd May 2025It's not in their [release notes](https://docs.anthropic.com/en/release-notes/claude-apps) yet but Anthropic pushed some big new features today. [Alex Albert](https://twitter.com/alexalbert__/status/1918349277962879218): > We've improved web search and rolled it out worldwide to all paid …

#alexalbert #llmtooluse #deepresearch

LLMs @LLMs@activitypub.awakari.com

Claude feature drop It's not in their release notes yet but Anthropic pushed some big new fea...

https://simonwillison.net/2025/May/2/claude-search/#atom-everything

#alex-albert #anthropic #claude #llm-tool-use #deep-research #ai #llms #generative-ai

Result Details

Simon Willison’s WeblogNote on 2nd May 2025It's not in their [release notes](https://docs.anthropic.com/en/release-notes/claude-apps) yet but Anthropic pushed some big new features today. [Alex Albert](https://twitter.com/alexalbert__/status/1918349277962879218): > We've improved web search and rolled it out worldwide to all paid …

#alexalbert #llmtooluse #deepresearch

LLMs @LLMs@activitypub.awakari.com

Claude feature drop It's not in their release notes yet but Anthropic pushed some big new fea...

https://simonwillison.net/2025/May/2/claude-search/#atom-everything

#alex-albert #anthropic #claude #llm-tool-use #deep-research #ai #llms #generative-ai

Result Details

Simon Willison’s WeblogNote on 2nd May 2025It's not in their [release notes](https://docs.anthropic.com/en/release-notes/claude-apps) yet but Anthropic pushed some big new features today. [Alex Albert](https://twitter.com/alexalbert__/status/1918349277962879218): > We've improved web search and rolled it out worldwide to all paid …

#alexalbert #llmtooluse #deepresearch

LLMs @LLMs@activitypub.awakari.com

Xata Agent Xata Agent Xata are a hosted PostgreSQL company who also develop the open source pgrol...

https://simonwillison.net/2025/Mar/13/xata-agent/#atom-everything

#prompt-engineering #generative-ai #ai-agents #postgresql #ai #llms #llm-tool-use

Result Details

Simon Willison’s WeblogXata AgentXata are a hosted PostgreSQL company who also develop the open source [pgroll](https://github.com/xataio/pgroll) and [pgstream](https://github.com/xataio/pgstream) schema migration tools. Their new "Agent" tool is a system that helps monitor and optimize …

#promptengineering #generativeAI #aiagents

LLMs @LLMs@activitypub.awakari.com

AI assisted search-based research actually works now For the past two and a half years the featur...

https://simonwillison.net/2025/Apr/21/ai-assisted-search/#atom-everything

#gemini #anthropic #openai #llm-tool-use #o3 #search #ai #llms #google #generative-ai #perplexity

Result Details

Simon Willison’s WeblogAI assisted search-based research actually works nowFor the past two and a half years the feature I’ve most wanted from LLMs is the ability to take on search-based research tasks on my behalf. We saw the …

#llmtooluse #generativeAI

LLMs @LLMs@activitypub.awakari.com

AI assisted search-based research actually works now For the past two and a half years the featur...

https://simonwillison.net/2025/Apr/21/ai-assisted-search/#atom-everything

#gemini #anthropic #openai #llm-tool-use #o3 #search #ai #llms #google #generative-ai #perplexity

Result Details

#llmtooluse #generativeAI

LLMs @LLMs@activitypub.awakari.com

AI assisted search-based research actually works now For the past two and a half years the featur...

https://simonwillison.net/2025/Apr/21/ai-assisted-search/#atom-everything

#gemini #anthropic #openai #llm-tool-use #o3 #search #ai #llms #google #generative-ai #perplexity

Result Details

Simon Willison’s WeblogAI assisted search-based research actually works nowFor the past two and a half years the feature I’ve most wanted from LLMs is the ability to take on search-based research tasks on my behalf. We saw the …

#llmtooluse #generativeAI

LLMs @LLMs@activitypub.awakari.com

MCP Run Python MCP Run Python Pydantic AI's MCP server for running LLM-generated Python code ...

https://simonwillison.net/2025/Apr/18/mcp-run-python/#atom-everything

#deno #pydantic #uv #sandboxing #llm-tool-use #ai #llms #model-context-protocol #python #generative-ai #mistral

Event Attributes

Simon Willison’s WeblogMCP Run PythonPydantic AI's MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored [two years ago](https://til.simonwillison.net/deno/pyodide-sandbox): using a [Deno](https://deno.com/) process to run [Pyodide](https://pyodide.org/) …

#llmtooluse #modelcontextprotocol #generativeAI

LLMs @LLMs@activitypub.awakari.com

MCP Run Python MCP Run Python Pydantic AI's MCP server for running LLM-generated Python code ...

https://simonwillison.net/2025/Apr/18/mcp-run-python/#atom-everything

#deno #pydantic #uv #sandboxing #llm-tool-use #ai #llms #model-context-protocol #python #generative-ai #mistral

Event Attributes

Simon Willison’s WeblogMCP Run PythonPydantic AI's MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored [two years ago](https://til.simonwillison.net/deno/pyodide-sandbox): using a [Deno](https://deno.com/) process to run [Pyodide](https://pyodide.org/) …

#llmtooluse #modelcontextprotocol #generativeAI

LLMs @LLMs@activitypub.awakari.com

MCP Run Python MCP Run Python Pydantic AI's MCP server for running LLM-generated Python code ...

https://simonwillison.net/2025/Apr/18/mcp-run-python/#atom-everything

#deno #pydantic #uv #sandboxing #llm-tool-use #ai #llms #model-context-protocol #python #generative-ai #mistral

Event Attributes

Simon Willison’s WeblogMCP Run PythonPydantic AI's MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored [two years ago](https://til.simonwillison.net/deno/pyodide-sandbox): using a [Deno](https://deno.com/) process to run [Pyodide](https://pyodide.org/) …

#llmtooluse #modelcontextprotocol #generativeAI

LLMs @LLMs@activitypub.awakari.com

Introducing OpenAI o3 and o4-mini Introducing OpenAI o3 and o4-mini OpenAI are really emphasizing...

https://simonwillison.net/2025/Apr/16/introducing-openai-o3-and-o4-mini/#atom-everything

#llm #openai #llm-tool-use #llm-pricing #ai #llms #llm-release #generative-ai #llm-reasoning

Event Attributes

Simon Willison’s WeblogIntroducing OpenAI o3 and o4-miniOpenAI are *really* emphasizing tool use with these: > For the first time, our reasoning models can agentically use and combine every tool within ChatGPT—this includes searching the web, analyzing …

#llmtooluse #llmpricing #llmrelease

LLMs @LLMs@activitypub.awakari.com

Introducing OpenAI o3 and o4-mini Introducing OpenAI o3 and o4-mini OpenAI are really emphasizing...

https://simonwillison.net/2025/Apr/16/introducing-openai-o3-and-o4-mini/#atom-everything

#llm #openai #llm-tool-use #llm-pricing #ai #llms #llm-release #generative-ai #inference-scaling

Event Attributes

Simon Willison’s WeblogIntroducing OpenAI o3 and o4-miniOpenAI are *really* emphasizing tool use with these: > For the first time, our reasoning models can agentically use and combine every tool within ChatGPT—this includes searching the web, analyzing …

#llmtooluse #llmpricing #llmrelease

LLMs @LLMs@activitypub.awakari.com

Introducing OpenAI o3 and o4-mini Introducing OpenAI o3 and o4-mini OpenAI are really emphasizing...

https://simonwillison.net/2025/Apr/16/introducing-openai-o3-and-o4-mini/#atom-everything

#llm #openai #llm-tool-use #llm-pricing #ai #llms #llm-release #generative-ai #inference-scaling

Event Attributes

#llmtooluse #llmpricing #llmrelease

LLMs @LLMs@activitypub.awakari.com

Model Context Protocol has prompt injection security problems As more people start hacking around...

https://simonwillison.net/2025/Apr/9/mcp-prompt-injection/#atom-everything

#security #ai #prompt-injection #generative-ai #llms #exfiltration-attacks #llm-tool-use #ai-agents #model-context-protocol

Event Attributes

Simon Willison’s WeblogModel Context Protocol has prompt injection security problemsAs more people start hacking around with implementations of MCP (the Model Context Protocol, a new standard for making tools available to LLM-powered systems) the security implications of tools built …

#promptinjection #generativeAI #exfiltrationattacks

LLMs @LLMs@activitypub.awakari.com

Model Context Protocol has prompt injection security problems As more people start hacking around...

https://simonwillison.net/2025/Apr/9/mcp-prompt-injection/#atom-everything

#security #ai #prompt-injection #generative-ai #llms #exfiltration-attacks #llm-tool-use #ai-agents #model-context-protocol

Event Attributes

#promptinjection #generativeAI #exfiltrationattacks

SearchEngine @SearchEngine@activitypub.awakari.com

debug-gym debug-gym New paper and code from Microsoft Research that experiments with giving LLMs ...

https://simonwillison.net/2025/Mar/31/debug-gym/#atom-everything

#prompt-engineering #llms #python #generative-ai #llm-tool-use #ai #microsoft #claude

Event Attributes

Simon Willison’s Weblogdebug-gymNew paper and code from Microsoft Research that experiments with giving LLMs access to the Python debugger. They found that the best models could indeed improve their results by running …

#promptengineering #generativeAI #llmtooluse

SearchEngine @SearchEngine@activitypub.awakari.com

debug-gym debug-gym New paper and code from Microsoft Research that experiments with giving LLMs ...

https://simonwillison.net/2025/Mar/31/debug-gym/#atom-everything

#prompt-engineering #llms #python #generative-ai #llm-tool-use #ai #microsoft #claude

Event Attributes

Simon Willison’s Weblogdebug-gymNew paper and code from Microsoft Research that experiments with giving LLMs access to the Python debugger. They found that the best models could indeed improve their results by running …

#promptengineering #generativeAI #llmtooluse

LLMs @LLMs@activitypub.awakari.com

debug-gym debug-gym New paper and code from Microsoft Research that experiments with giving LLMs ...

https://simonwillison.net/2025/Mar/31/debug-gym/#atom-everything

#prompt-engineering #llms #python #generative-ai #llm-tool-use #ai #microsoft #claude

Event Attributes

Simon Willison’s Weblogdebug-gymNew paper and code from Microsoft Research that experiments with giving LLMs access to the Python debugger. They found that the best models could indeed improve their results by running …

#promptengineering #generativeAI #llmtooluse

Trascina e rilascia per caricare