⚡️ F# Weekly #24, 2026
🏷️ #devdigest #dotnet #net #jetbrains #ide #rider #microsoft #ide #vscode #microsoft #ide #visualstudio #cloud #azure #fp #fsharp #microsoft #net
devdigest.today/goto/6637
12
⚡️ Microsoft Releases .NET 11 Preview 5
🏷️ #devdigest #dotnet #net #microsoft #ide #visualstudio #csharp #maui #microsoft #net #aspnet #asp
devdigest.today/goto/6636
13
Jun 12
🎥 Build 2026: Microsoft introduced the largest Azure service pack
🏷️ #devdigest #azure #cloud #cloud #azure #microsoft
devdigest.today/post/6635
7
Jun 12
⚡️ .NET 11: Runtime Async, Native AOT, and AI Application Development Tools
🏷️ #devdigest #dotnet #net #microsoft #net
devdigest.today/goto/6634
6
Jun 9
1
1
32
Jun 8
⚡️ HybridCache is a single API for two-tier caching
🏷️ #devdigest #dotnet #net
devdigest.today/goto/6632
1
25
Carlos Tecnico retweeted
Jun 7
💯
“good tools are cached intelligence for agents”
Jun 5
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents!
The popular theory goes: agents can write code, so they'll just rebuild every tool from scratch and hit raw APIs. no more dev tools, no more CLIs, no more software layers. just agents and endpoints!
We just tested this and the data says the opposite. We benchmarked Claude Code and Codex on real Hugging Face Hub tasks (~1,000 graded runs), with two setups: the agent-optimized hf CLI vs the agent hand-rolling curl or SDK calls from scratch.
Hand-rolling burns up to 6x more tokens on multi-step tasks and fails more often (84% vs 94% task success).
And that's just dropping one abstraction layer. It would obviously be orders of magnitude more tokens and a dramatically higher failure rate if the agent tried to bypass HF altogether and rebuild model hosting, versioning, and distribution from scratch. Every time an agent re-derives a workflow from raw API calls, you pay for that reasoning in tokens. every single run. a good CLI compresses that entire chain into a few high-level commands the agent can't get wrong.
In a world where everyone is complaining tokens are too expensive, abstraction is leverage: thousands of hours of design decisions your agent doesn't have to re-reason about at inference time.
Good tools are cached intelligence for agents!
So no, agents won't rebuild everything from scratch. they'll gravitate to the most token-efficient tools, because that's what their owners pay for. The software that survives won't just be accessible to agents, it will be accurate and cheap for them to drive.
We're seeing it happen with HF, which is becoming the platform for agents to use AI: ~49M requests in just two months, and growing fast!
huggingface.co/blog/hf-cli-f…
1
1
318
Jun 2
⚡️ Memory in C# will become noticeably safer
🏷️ #devdigest #dotnet #net #csharp #microsoft
devdigest.today/goto/6631
1
27
May 28
⚡️ .NET API under 1 million requests per minute
🏷️ #devdigest #dotnet #net #aspnet #asp
devdigest.today/goto/6630
20
May 26
📢 LATEST UPDATE: X announces its official digital currency debut 🚀
👥 Invited: @neneng_bang @devdigest @elchuzade x.com/i/spaces/1pKkOOXADorKj
📌 More Info in Article Below 👇👇👇
2
May 23
⚡️ dotInsights | May 2026
🏷️ #devdigest #dotnet #net #jetbrains #ide #rider #csharp
devdigest.today/goto/6507
1
33
May 21
@Spookitty_Sol @L1ghtovi @chriswilton30 @MRizkyRamdani11 @MAKOTO764841 @msr54797 @SirChsterton @lorine28cupid @xiao92383554931 @Adesina0113 @doublebottow @CodyHazard3 @BitchRelie68079 @Solmax0 @BbtcMarcel47815 @naramurakchohi @robert_hunner @oxxxlong @devdigest @sjh3u #KnLnSlADyrhufTn9a5VNXuC1HS8osRJKlima4n48MXlPVbtv42Hn2ACGgJeIsknfpmCgIQmdlzVroA5gzWuebqDkcpIFpiLylmSv x.com/i/lists/20575235289670… x.com/i/spaces/1OxwbldZPOLJB
May 20
29
May 16
⚡️ In .NET, MAUI will default to CoreCLR
🏷️ #devdigest #dotnet #net #cloud #azure #maui #microsoft #aspnet #asp
devdigest.today/goto/6533
1
52
It’s been an incredible day at @langchain Interrupt! So many talented people and incredible conversations!
4
91