How OpenAI stores data for 1B ChatGPT users 🚀
OpenAI published part two of the storage work behind ChatGPT, Codex, and API workloads at billion-user scale.
Habitat is the storage platform in the middle. It uses Azure Cosmos DB multi-tenancy, caching, and data placement so workloads can scale without every product team rebuilding its own persistence layer.
What matters:
• Multi-tenancy: isolate customer and workload data without multiplying operational overhead.
• Cache-aware reads: keep hot data off the expensive path.
• Placement controls: put data near the workload that needs it.
This is the less glamorous half of AI infrastructure. Models get the headlines. Storage latency, tenancy boundaries, and cache hit rates decide whether the product survives traffic.
[ Read More ] :
https://openai.com/index/scaling-storage-one-billion-users-part-two/
〰〰〰〰〰〰
#AI #OpenAI #Azure #Storage
@ProgrammingTip
OpenAI published part two of the storage work behind ChatGPT, Codex, and API workloads at billion-user scale.
Habitat is the storage platform in the middle. It uses Azure Cosmos DB multi-tenancy, caching, and data placement so workloads can scale without every product team rebuilding its own persistence layer.
What matters:
• Multi-tenancy: isolate customer and workload data without multiplying operational overhead.
• Cache-aware reads: keep hot data off the expensive path.
• Placement controls: put data near the workload that needs it.
This is the less glamorous half of AI infrastructure. Models get the headlines. Storage latency, tenancy boundaries, and cache hit rates decide whether the product survives traffic.
[ Read More ] :
https://openai.com/index/scaling-storage-one-billion-users-part-two/
〰〰〰〰〰〰
#AI #OpenAI #Azure #Storage
@ProgrammingTip
OpenAI
Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II)
Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT.
GPT-6.1 Terra is in the OpenAI API 🚀
OpenAI introduced GPT-6.1 Terra for developers who need computer use without paying for a slower, heavier model on every task.
Call it as
What to test first:
• Long UI runs: can it recover after a modal, redirect, or failed click?
• Tool boundaries: keep payments, deletes, and production writes behind explicit approval.
• Cost per completed task: token price is not the whole bill when retries are involved.
Computer use is getting cheaper. Your eval suite now matters more than a demo.
[ Read More ] :
https://openai.com/index/introducing-gpt-6-1-terra/
〰〰〰〰〰〰
#AI #OpenAI #API #Agents
@ProgrammingTip
OpenAI introduced GPT-6.1 Terra for developers who need computer use without paying for a slower, heavier model on every task.
Call it as
gpt-6.1-terra. The pitch is fast UI interaction, capable multi-step work, and lower standard pricing. That makes it a practical model to test for browser agents, QA flows, back-office automation, and anything that has to click through a real app.What to test first:
• Long UI runs: can it recover after a modal, redirect, or failed click?
• Tool boundaries: keep payments, deletes, and production writes behind explicit approval.
• Cost per completed task: token price is not the whole bill when retries are involved.
Computer use is getting cheaper. Your eval suite now matters more than a demo.
[ Read More ] :
https://openai.com/index/introducing-gpt-6-1-terra/
〰〰〰〰〰〰
#AI #OpenAI #API #Agents
@ProgrammingTip
OpenAI
Introducing GPT-6.1 Terra
Delivering fast and capable computer use at scale
NuGet packages can deliver agent skills 🔥
Microsoft is showing how to ship skills in NuGet packages.
The idea is simple: a package can carry more than assemblies, analyzers, and build targets. It can also deliver instructions and reusable capability definitions that coding agents can discover in a repo.
Why this is useful:
• Package authors can document the right workflow next to the API.
• App teams get consistent agent guidance when they install a dependency.
• Platform teams can distribute internal conventions without pasting the same prompt into every project.
Treat these skills like any other package surface. Version them, keep the instructions narrow, and test them against real agent tasks before publishing.
[ Blog ] :
https://devblogs.microsoft.com/dotnet/delivering-skills-in-nuget-packages/
〰〰〰〰〰〰
#dotnet #NuGet #CSharp #AI
@ProgrammingTip
Microsoft is showing how to ship skills in NuGet packages.
The idea is simple: a package can carry more than assemblies, analyzers, and build targets. It can also deliver instructions and reusable capability definitions that coding agents can discover in a repo.
Why this is useful:
• Package authors can document the right workflow next to the API.
• App teams get consistent agent guidance when they install a dependency.
• Platform teams can distribute internal conventions without pasting the same prompt into every project.
Treat these skills like any other package surface. Version them, keep the instructions narrow, and test them against real agent tasks before publishing.
[ Blog ] :
https://devblogs.microsoft.com/dotnet/delivering-skills-in-nuget-packages/
〰〰〰〰〰〰
#dotnet #NuGet #CSharp #AI
@ProgrammingTip
Claude Fable 5.2 and Mythos 5.2 are out 🚀
Anthropic shipped Claude Fable 5.2 and Mythos 5.2.
The useful part for teams is simple: model swaps are not just a leaderboard event. They change what your eval suite needs to catch before you update a production alias.
Before switching:
• Run your real tool-call and structured-output cases.
• Check retry rates, latency, and token use.
• Keep a small regression set for the weird customer inputs.
A new model can write cleaner code and still break one JSON edge case that your old one handled. Pin versions where you can, test the candidate, then move traffic deliberately.
[ Article ] :
https://www.anthropic.com/claude-fable-and-mythos-5-2
〰〰〰〰〰〰
#AI #LLM #Claude
@ProgrammingTip
Anthropic shipped Claude Fable 5.2 and Mythos 5.2.
The useful part for teams is simple: model swaps are not just a leaderboard event. They change what your eval suite needs to catch before you update a production alias.
Before switching:
• Run your real tool-call and structured-output cases.
• Check retry rates, latency, and token use.
• Keep a small regression set for the weird customer inputs.
A new model can write cleaner code and still break one JSON edge case that your old one handled. Pin versions where you can, test the candidate, then move traffic deliberately.
[ Article ] :
https://www.anthropic.com/claude-fable-and-mythos-5-2
〰〰〰〰〰〰
#AI #LLM #Claude
@ProgrammingTip
Anthropic
Introducing Claude Fable 5.2 and Claude Mythos 5.2
Claude Fable 5.2 and Claude Mythos 5.2, our new models for the hardest technical challenges. Fable 5.2 sets a new bar in coding, finance, and the sciences.
.NET 11 is out 🔥
.NET 11 has landed. The first practical move is not changing every project file. Get the SDK into CI, build a representative solution, and make the failures visible.
Start with:
• Install the .NET 11 SDK in a non-production pipeline.
• Test
• Review package compatibility, analyzers, source generators, and native dependencies.
• Pin the SDK with
A major runtime release is a good excuse to delete old workarounds too. Run benchmarks before and after, especially around hot APIs, JSON, HTTP, and startup. "It builds" is only the first green check.
[ Blog ] :
https://devblogs.microsoft.com/dotnet/announcing-dotnet-11/
〰〰〰〰〰〰
#dotnet #csharp #dotnet11
@ProgrammingTip
.NET 11 has landed. The first practical move is not changing every project file. Get the SDK into CI, build a representative solution, and make the failures visible.
Start with:
• Install the .NET 11 SDK in a non-production pipeline.
• Test
net11.0 alongside your current target framework.• Review package compatibility, analyzers, source generators, and native dependencies.
• Pin the SDK with
global.json before developers get different local results.A major runtime release is a good excuse to delete old workarounds too. Run benchmarks before and after, especially around hot APIs, JSON, HTTP, and startup. "It builds" is only the first green check.
[ Blog ] :
https://devblogs.microsoft.com/dotnet/announcing-dotnet-11/
〰〰〰〰〰〰
#dotnet #csharp #dotnet11
@ProgrammingTip