WAGMI dotnet tool install -g MandoCode #ai #llm

GLM-5.2 I asked "Make super mario game" , 192k tokens later. pretty cool

One thing I've learned building AI agents is that reliability matters just as much as intelligence. MandoCode v0.12.0 is out 🚀 This release fixes several long-session issues including: • Agent loops freezing during file approval • Command execution deadlocks • Duplicated/garbled output rendering • Repeated web search loops • Browser preview stalls Every fix is covered by automated tests, bringing the suite to 449 checks. Building agentic systems has taught me that the hardest bugs aren't usually model-related—they're state, orchestration, and reliability problems. #dotnet #ai #semantickernel #ollama #opensource #agenticai github.com/DevMando/MandoCod…

Taking the day away from #ai #llms #agents. These will go in the smoker today 😎

If you are building agents and think system prompts don't play a big role, this repo can give some perspective on how frontier models are being shaped by their system prompt github.com/elder-plinius/CL4…

Tokens are starting to feel like rollover minutes back in the 2ks using cell phones. #ai

Same! Building MandoCode a CLI agent that utilizes Ollama models. 😎. github.com/DevMando/MandoCod…

Late nights with llms

Claude = Netflix Open weight local models = DVDs Hoard DVDs even if they are of low quality. A good engineer with a good local model is a good combo. #ai #claude #anthropic

.@Kimi_Moonshot's kimi-k2.7-code is now available on Ollama's cloud! On Ollama's cloud, this model is hosted in the US on the latest NVIDIA B300 datacenter GPUs. Your data stays private and is never trained on. ❤️❤️❤️ Try the model: Claude: ollama launch claude --model kimi-k2.7-code:cloud Codex App: ollama launch codex-app --model kimi-k2.7-code:cloud OpenCode ollama launch opencode --model kimi-k2.7-code:cloud See the model page on Ollama 👇👇👇

I miss Fable already... Lol #fable #claude

A new definition of close source model🐮

We've reset 5-hour and weekly rate limits for all users.

As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models. Here’s what this means for you: Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error. On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models. We know this is a disruption to your workflows; we appreciate your patience and support.

sick

MandoCode v0.11.0 is OUT! 😎🎉 This one was a huge update, with additional development on making sure agentic loops actually finished planned steps formed to complete a task. Build on C# and #dotNet #ai #agents #agentic #ollama dotnet tool update -g MandoCode github.com/DevMando/MandoCod…

Current situation #knicks #claude #ai

Fable5 is a new type of beast. hands down the best model, hands down the most expensive lol, but I love it. #ai #mythos

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time. I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

If you’re having trouble accessing Claude Fable 5, try running /model claude-fable-5. In the Claude Code CLI, make sure to upgrade to 2.1.170. If you’re on the Claude Desktop app, update the latest version.

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.