Daniel Ward - daninacan

234 posts

Daniel Ward - daninacan banner
Daniel Ward - daninacan

Daniel Ward - daninacan

@danielwarddev

Microsoft MVP .NET Software dev, consultant Average .NET enjoyer Co-organizer of the San Antonio/Austin .NET User Group Game dev using Godot/Unity

San Antonio, TX Se unió Mayıs 2022
152 Siguiendo143 Seguidores
Burke Holland
Burke Holland@burkeholland·
Checkout this PowerPoint MCP Server from @trsdn. Look at all these tools! Animations, Charts, Media, SmartArt, VBA?!?! I've not tried it yet, but definitely something to add to your @GitHub Copilot CLI or OpenClaw. Windows only tho. Sry. Link 👇
Burke Holland tweet media
English
4
4
40
2.6K
Daniel Ward - daninacan
Daniel Ward - daninacan@danielwarddev·
Want to build cross-platform apps with one codebase? Next week's .NET@Noon will go over .NET MAUI! #dotnet 🎤What: MAUI: The Tropical Paradise of Multi-Platform Development 👨‍🏫Who: Jeff Shafferman ⌚When: February 26 @ Noon CST 🌐Where: Zoom Signup here: meetup.com/sadnug/events/…
Daniel Ward - daninacan tweet media
English
0
2
2
73
Oren Melamed
Oren Melamed@OrenMe·
The @code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.
English
36
26
232
29.4K
Brian Gorman
Brian Gorman@blgorman·
@danielwarddev ah, lost my check, can't edit. So it's not a chapter on testcontainers - it's a chapter on testing (unit and integration) and part of that is on test containers :)
English
2
0
2
40
Daniel Ward - daninacan
Daniel Ward - daninacan@danielwarddev·
@burkeholland I would say I'm cautiously optimistic right now. From what I've seen, AI doesn't change any of the underlying practices of SDLC, and that includes small batches. I guess if you use RW to do that, and review in between, that would be a good use. Still experimenting myself though!
English
0
0
1
43
Burke Holland
Burke Holland@burkeholland·
I'm hesitant to promote these agents loops because I feel like being part of said loop is super important. That said, it seems like people are having a lot of success with them, which is ultimately all that matters.
Oren Melamed@OrenMe

The Ralph hype is kind of funny. Someone wired it to run inside @code and… that’s actually interesting. A dedicated UI + a proper execution loop makes the whole thing feel real solid. The UI harness looks great, the implementation is clean, and it genuinely feels nice to use. Ironically, most of this is achievable with a strong prompt and heavy use of sub-agents, skills, maybe custom agents. But once you wrap it with a dedicated UI, it hits differently. Would love to see more UI harnesses like this for agent tools in @code Great work @yanashin18618 👏

English
4
0
13
3K
Daniel Ward - daninacan
Daniel Ward - daninacan@danielwarddev·
Thank you to everyone who came out for the San Antonio #dotNETConf! It was the first event of the year for the SA .NET User Group and the turnout + whole event was great! Also big thanks to @leantechniques for sponsoring, @Geekdom for hosting, and @devsatx for collab!
Daniel Ward - daninacan tweet media
English
0
1
2
88
Daniel Ward - daninacan
Daniel Ward - daninacan@danielwarddev·
I know a lot of others tools like CC have more shiny stuff, but goodness the value you get out of GH Copilot's premium requests model is insane. I just had Opus 4.5 work on a request for probably about an hour and it only cost me 3 of my 300 premium requests for the month lol
English
1
0
1
47
Daniel Ward - daninacan
Daniel Ward - daninacan@danielwarddev·
This Saturday will be San Antonio's local .NET Conf! We'll go over the highlights of all the new .NET 10 updates condensed into an hour. #dotNETConf 📍In-person at Geekdom, Jan 10 @ 1 PM 🌮Food/drinks provided 🎉Come learn with your fellow devs! Signup: meetup.com/sadnug/events/…
Daniel Ward - daninacan tweet media
English
0
0
0
68