Lars Grammel
@lars.grammel.cloud
Humans have been writing software for about 75 years. AIs will write software for hundreds and thousands of years.
Eventually everything - hardware, OS, libraries, APIS, services, applications - will be designed to facilitate AI software development.
Eventually everything - hardware, OS, libraries, APIS, services, applications - will be designed to facilitate AI software development.
February 19, 2026 at 10:01 AM
Humans have been writing software for about 75 years. AIs will write software for hundreds and thousands of years.
Eventually everything - hardware, OS, libraries, APIS, services, applications - will be designed to facilitate AI software development.
Eventually everything - hardware, OS, libraries, APIS, services, applications - will be designed to facilitate AI software development.
one of the best articles on the future of agentic coding that i've read so far: openai.com/index/harnes...
Harness engineering: leveraging Codex in an agent-first world
By Ryan Lopopolo, Member of the Technical Staff
openai.com
February 18, 2026 at 3:01 PM
one of the best articles on the future of agentic coding that i've read so far: openai.com/index/harnes...
Been thinking a lot about git lately and how incredibly well designed it is.
February 18, 2026 at 1:59 PM
Been thinking a lot about git lately and how incredibly well designed it is.
future software will be developed in dark software factories by a variety of ai agents operating on a shared code repository infrastructure optimized for those agents. humans won't look at the code any more, similar to how we do not look at assembly today.
I wrote about the most ambitious form of AI-assisted software development I've seen yet - Strong DM's "Software Factory" approach, where two of the guiding principles are "Code must not be written by humans" and "Code must not be reviewed by humans" simonwillison.net/2026/Feb/7/s...
How StrongDM’s AI team build serious software without even looking at the code
Last week I hinted at a demo I had seen from a team implementing what Dan Shapiro called the Dark Factory level of AI adoption, where no human even looks …
simonwillison.net
February 12, 2026 at 2:47 PM
future software will be developed in dark software factories by a variety of ai agents operating on a shared code repository infrastructure optimized for those agents. humans won't look at the code any more, similar to how we do not look at assembly today.
in a future where ai agents write all the code, libraries and frameworks are somewhat dead bc they include overhead unnecessary for the specific use cases of the software and represent a supply chain risk
February 12, 2026 at 2:47 PM
in a future where ai agents write all the code, libraries and frameworks are somewhat dead bc they include overhead unnecessary for the specific use cases of the software and represent a supply chain risk
My talk about AI SDK 5 from the AI Meetup in Wrocław is on youtube: www.youtube.com/watch?v=xgR-...
AI SDK 5: What’s New and What’s Next by Lars Grammel | AI Meetup in Wrocław, September 2025
YouTube video by Callstack
www.youtube.com
October 12, 2025 at 7:38 AM
My talk about AI SDK 5 from the AI Meetup in Wrocław is on youtube: www.youtube.com/watch?v=xgR-...
prediction: as ai relies more and more on websearch, seo for ai will bring product placement and then it will be followed by ads for ai (content suggestions), esp. in free ai chatbot tiers. ai chatbots will become more like google search in some of those ways.
September 7, 2025 at 2:23 PM
prediction: as ai relies more and more on websearch, seo for ai will bring product placement and then it will be followed by ads for ai (content suggestions), esp. in free ai chatbot tiers. ai chatbots will become more like google search in some of those ways.
I find this research fascinating because it means that there is a path towards smaller models that are strong on tool use and reasoning and that use external knowledge sources (through tools such as web search) instead of baked in knowledge.
openai.com/index/why-la...
openai.com/index/why-la...
September 7, 2025 at 2:16 PM
I find this research fascinating because it means that there is a path towards smaller models that are strong on tool use and reasoning and that use external knowledge sources (through tools such as web search) instead of baked in knowledge.
openai.com/index/why-la...
openai.com/index/why-la...
Reposted by Lars Grammel
The previously sensible advice to never use ChatGPT for search needs to be rethought - GPT-5 in thinking mode is shockingly good at running searches now simonwillison.net/2025/Sep/6/r...
GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
“Don’t use chatbots as search engines” was great advice for several years... until it wasn’t. I wrote about how good OpenAI’s o3 was at using its Bing-backed search tool back …
simonwillison.net
September 6, 2025 at 7:44 PM
The previously sensible advice to never use ChatGPT for search needs to be rethought - GPT-5 in thinking mode is shockingly good at running searches now simonwillison.net/2025/Sep/6/r...
At React Universe Conference Wroclaw today - would love to chat with AI SDK users.
If you are around and want to give feedback or learn more about the AI SDK send me a DM.
If you are around and want to give feedback or learn more about the AI SDK send me a DM.
September 3, 2025 at 9:43 AM
At React Universe Conference Wroclaw today - would love to chat with AI SDK users.
If you are around and want to give feedback or learn more about the AI SDK send me a DM.
If you are around and want to give feedback or learn more about the AI SDK send me a DM.
Finally - almost 5 months of work, our biggest release so far.
Completely revamped, type-safe AI chat is a game changer imo. I don't know any other framework that has full stack support for this. Hope it will enable you to build the next generation of AI applications.
Completely revamped, type-safe AI chat is a game changer imo. I don't know any other framework that has full stack support for this. Hope it will enable you to build the next generation of AI applications.
AI SDK 5
Introducing type-safe chat, agentic loop controls, data parts, speech generation and transcription, Zod 4 support, global provider, and raw request access.
Introducing type-safe chat, agentic loop controls, data parts, speech generation and transcription, Zod 4 support, global provider, and raw request access.
July 31, 2025 at 4:15 PM
Finally - almost 5 months of work, our biggest release so far.
Completely revamped, type-safe AI chat is a game changer imo. I don't know any other framework that has full stack support for this. Hope it will enable you to build the next generation of AI applications.
Completely revamped, type-safe AI chat is a game changer imo. I don't know any other framework that has full stack support for this. Hope it will enable you to build the next generation of AI applications.
You can try AI SDK 5 now:
AI SDK 5 Alpha (Early Preview)
An entirely new foundation with LanguageModelV2, a rearchitected useChat, new agentic controls and more.
Play with the alpha release and help us improve it.
Disclaimer: not yet ready for production use or migrating existing projects.
An entirely new foundation with LanguageModelV2, a rearchitected useChat, new agentic controls and more.
Play with the alpha release and help us improve it.
Disclaimer: not yet ready for production use or migrating existing projects.
May 16, 2025 at 1:40 PM
You can try AI SDK 5 now:
AI SDK 5 prototype: custom UI data parts
You can define custom ui data parts and stream updates to them from the server:
You can define custom ui data parts and stream updates to them from the server:
May 14, 2025 at 5:44 PM
AI SDK 5 prototype: custom UI data parts
You can define custom ui data parts and stream updates to them from the server:
You can define custom ui data parts and stream updates to them from the server:
AI SDK 5 preview: ChatStore & ChatTransport
ChatStore synchronizes chat write operations and manages streaming state. You can use it directly or through framework integrations like useChat.
ChatTransport makes backend integrations more flexible, allowing for client-only usage.
ChatStore synchronizes chat write operations and manages streaming state. You can use it directly or through framework integrations like useChat.
ChatTransport makes backend integrations more flexible, allowing for client-only usage.
May 13, 2025 at 3:05 PM
AI SDK 5 preview: ChatStore & ChatTransport
ChatStore synchronizes chat write operations and manages streaming state. You can use it directly or through framework integrations like useChat.
ChatTransport makes backend integrations more flexible, allowing for client-only usage.
ChatStore synchronizes chat write operations and manages streaming state. You can use it directly or through framework integrations like useChat.
ChatTransport makes backend integrations more flexible, allowing for client-only usage.
AI SDK 5 preview: UI message persistance
We recommend storing UI messages, not model messages, if your application has a useChat component.
This ensures that the UI state can be correctly restored and helps integrating backends other than streamText (e.g. Langchain).
We recommend storing UI messages, not model messages, if your application has a useChat component.
This ensures that the UI state can be correctly restored and helps integrating backends other than streamText (e.g. Langchain).
May 11, 2025 at 12:26 PM
AI SDK 5 preview: UI message persistance
We recommend storing UI messages, not model messages, if your application has a useChat component.
This ensures that the UI state can be correctly restored and helps integrating backends other than streamText (e.g. Langchain).
We recommend storing UI messages, not model messages, if your application has a useChat component.
This ensures that the UI state can be correctly restored and helps integrating backends other than streamText (e.g. Langchain).
AI SDK 5 preview: UI message metadata
UI messages in AI SDK 5 will have a generic metadata property (instead of specific properties like createdAt).
This lets you send and show the message metadata that's important in your application:
UI messages in AI SDK 5 will have a generic metadata property (instead of specific properties like createdAt).
This lets you send and show the message metadata that's important in your application:
May 10, 2025 at 4:53 PM
AI SDK 5 preview: UI message metadata
UI messages in AI SDK 5 will have a generic metadata property (instead of specific properties like createdAt).
This lets you send and show the message metadata that's important in your application:
UI messages in AI SDK 5 will have a generic metadata property (instead of specific properties like createdAt).
This lets you send and show the message metadata that's important in your application:
UI messages != model messages
What you display to the user (ui messages) is different from what you want to send to the LLM (model messages).
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
What you display to the user (ui messages) is different from what you want to send to the LLM (model messages).
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
May 10, 2025 at 4:52 PM
UI messages != model messages
What you display to the user (ui messages) is different from what you want to send to the LLM (model messages).
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
What you display to the user (ui messages) is different from what you want to send to the LLM (model messages).
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
In AI SDK 5, UI messages will be composed of parts.
This is my current vision of how UI messages could look like - feedback welcome.
This is my current vision of how UI messages could look like - feedback welcome.
May 10, 2025 at 4:49 PM
In AI SDK 5, UI messages will be composed of parts.
This is my current vision of how UI messages could look like - feedback welcome.
This is my current vision of how UI messages could look like - feedback welcome.
Starting to be excited about AI SDK 5
Our planned timeline:
- alpha 1st half of May
- beta 2nd half of May
- GA in June
Our planned timeline:
- alpha 1st half of May
- beta 2nd half of May
- GA in June
May 10, 2025 at 4:47 PM
Starting to be excited about AI SDK 5
Our planned timeline:
- alpha 1st half of May
- beta 2nd half of May
- GA in June
Our planned timeline:
- alpha 1st half of May
- beta 2nd half of May
- GA in June
AI agents vs workflow runs & run termination:
Workflows have a deterministic number of steps after which they will finish with with a solution (of varying quality).
Agents run in a loop and it is unclear when and if they will finish with a solution.
Workflows have a deterministic number of steps after which they will finish with with a solution (of varying quality).
Agents run in a loop and it is unclear when and if they will finish with a solution.
one fundamental issue w/ ai agents:
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
April 29, 2025 at 11:06 AM
AI agents vs workflow runs & run termination:
Workflows have a deterministic number of steps after which they will finish with with a solution (of varying quality).
Agents run in a loop and it is unclear when and if they will finish with a solution.
Workflows have a deterministic number of steps after which they will finish with with a solution (of varying quality).
Agents run in a loop and it is unclear when and if they will finish with a solution.
one fundamental issue w/ ai agents:
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
April 27, 2025 at 6:58 AM
one fundamental issue w/ ai agents:
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
the problem of deciding when to stop an agent run is a variant of the halting problem
there will always be agent runs for which, given their current state and history, it cannot be known whether they will terminate with an answer or not
Combining the provider registry with custom providers and middleware is extremely powerful for setting up your models in one place:
March 26, 2025 at 5:48 PM
Combining the provider registry with custom providers and middleware is extremely powerful for setting up your models in one place:
You can set custom headers, e.g. for auth, when using the MCP SSE transport:
March 24, 2025 at 5:04 PM
You can set custom headers, e.g. for auth, when using the MCP SSE transport:
Lots of new features shipped since January, check out our 4.2 release:
March 21, 2025 at 10:34 AM
Lots of new features shipped since January, check out our 4.2 release:
The AI SDK now supports LLMs that generate file outputs, first example are images:
March 19, 2025 at 1:24 PM
The AI SDK now supports LLMs that generate file outputs, first example are images:
