Trajectory, distance, speed, and comms delay are computed from NASA's published Artemis II mission plan parameters, not pulled live from NASA telemetry.

Also, the current discrepancy is likely caused by the orbital phase and reference model being used.

Right now the tracker shows about 192,000 km, while NASA's AROW shows about 80,000 miles, which is roughly 129,000 km. So yes, that is off by around 60,000 km. Difference can happen because the spacecraft is in a elliptical orbit and different trackers may be using different assumptions, interpolation methods,... or reference points for the trajectory.

Trajectory, distance, speed, and comms delay are computed from NASA’s published Artemis II mission plan parameters, not pulled live from NASA telemetry.

Also, the current discrepancy is likely caused by the orbital phase and reference model being used. Right now the tracker shows about 192,000 km, while NASA’s AROW shows about 80,000 miles, which is roughly 129,000 km. So yes, that is off by around 60,000 km.

difference can happen because the spacecraft is in a elliptical orbit and different trackers may be using different assumptions, interpolation methods, .. or reference points for the trajectory.

https://artemis-ii-tracker.com/

For those of us who apparently need a dedicated place to monitor this mission instead of behaving like well-adjusted people.

Comments URL: https://news.ycombinator.com/item?id=47621438

Points: 154

# Comments: 61

Comments URL: https://news.ycombinator.com/item?id=44491848

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44338536

Points: 3

# Comments: 0

I've built a platform that lets anyone create their own voice-based AI tutor. To showcase what the platform can do, I've created a voice-based AI tutor for Stanford's famous CS229 Machine Learning course. I took the course myself and know how challenging it can be, so I built this to make it easier to follow and stick with.

It's free for now (as long as budget lasts) -> https://vivaverbalis.com/ml

The goal of my app is simple: Whether you're a student, teacher, or just curious, you can instantly spin up a conversational AI tutor, and share it, with whoever you want. Instructors can align tutors with their course content and share them with their students. I'm a lecturer myself, and I've used this in my own classroom

Upload any learning material or define your learning goals - and the platform will generate a personalized, voice-based AI tutor that teaches you through real conversation.

Voice and conversation are so essential for thinking and learning. That's why we do rubber duck debugging. That's why pair programming works. Voice has so much latency and bandwidth. When you talk out loud, when you think out loud, you bring ideas to life. You make space for exploration. You surface thoughts you didn't know you had.

Now pair that with a conversational AI that doesn't just answer questions, but guides you. One that helps you arrive at conclusions by yourself. That's where the real magic happens.

I deeply believe this will change how we learn.

Thanks everyone for trying this out! Let me know what you think!

Best,

Mo

Comments URL: https://news.ycombinator.com/item?id=44231771

Points: 5

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=44109701

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=43777660

Points: 6

# Comments: 1

Technically you can use the original Codex CLI with a local LLM - if your inference provider implements the OpenAI Chat Completions API, with function calling, etc. included.

But based on what I had in mind - the idea that small models can be really useful if optimized for very specific use cases - I figured the current architecture of Codex CLI wasn't the best fit for that. So instead of forking it, I started from scratch.

Here's the rough thinking behind it:

   1. You still have to manually set up and run your own inference server (e.g., with ollama, lmstudio, vllm, etc.).
   2. You need to ensure that the model you choose works well with Codex's pre-defined prompt setup and configuration.
   3. Prompting patterns for small open-source models (like phi-4-mini) often need to be very different - they don't generalize as well.
   4. The function calling format (or structured output) might not even be supported by your local inference provider.

   - Write the tool specifically to run _locally_ out of the box, no inference API server required.
   - Use model directly (currently for phi-4-mini via llama-cpp-python).
   - Optimize the prompt and execution logic _per model_ to get the best performance.

Technically you can use the original Codex CLI with a local LLM - if your inference provider implements the OpenAI Chat Completions API, with function calling, etc. included.

But based on what I had in mind - the idea that small models can be really useful if optimized for very specific use cases - I figured the current architecture of Codex CLI wasn't the best fit for that. So instead of forking it, I started from scratch.

Here's the rough thinking behind it:

   1. You still have to manually set up and run your own inference server (e.g., with ollama, lmstudio, vllm, etc.).
   2. You need to ensure that the model you choose works well with Codex's pre-defined prompt setup and configuration.
   3. Prompting patterns for small open-source models (like phi-4-mini) often need to be very different - they don't generalize as well.
   4. The function calling format (or structured output) might not even be supported by your local inference provider.

So I built this with a few assumptions in mind:

   - Write the tool specifically to run _locally_ out of the box, no inference API server required.
   - Use model directly (currently for phi-4-mini via llama-cpp-python).
   - Optimize the prompt and execution logic _per model_ to get the best performance.

Comments URL: https://news.ycombinator.com/item?id=43756675

Points: 4

# Comments: 0

Was the model too big to run locally?

That’s one of the reasons I went with phi-4-mini - surprisingly high quality for its size and speed. It handled multi-step reasoning, math, structured data extraction, and code pretty well, all on modest hardware. Phi-1.5 / Phi-2 (quantized versions) also run on raspberry pi as others have demonstrated.