Project Fetch: Can Claude train a robot dog?
…Limitations We learned a lot from Project Fetch, but the study clearly has shortcomings and limitations. This was only one experiment with two teams—an obviously small sample size. We only tested…
Search
All sources
xda-developers.com
26
androidauthority.com
2
anthropic.com
2
pcworld.com
1
huggingface.co
1
9to5mac.com
1
gamesindustry.biz
1
I ditched Claude Pro for free tools for a week — and one of them had no right being this good
…like stress-testing something I'd already assumed had limits I hadn't actually confirmed. Turns out I'd undersold it, and Canvas is the thing that changed the comparison for me…
I replaced ChatGPT with a local model on my gaming PC, and it's beating the cloud where I didn't expect
…garbage output in early testing on a Radeon RX 9700, the author later updating the comment to say Vulkan and Metal had been tested. Qwen's response was a clean, usable summary…
I let Claude audit my messy Home Assistant setup, and it was a massive wake-up call
…The biggest surprise wasn't that Claude could build an automation, it was watching it work around limitations. The AI immediately noticed the layout formatting error and tried to backspace over the…
Discussions and forums
Ask HN: Favorite prompts for improving LLM output?
I use Claude Code a lot and GPT 5.5 as well, and find that they are simultaneously extremely useful and also fall into common poor-performance basins. For example, writing performance -- perhaps my biggest issue with the…
2
1
Show HN: Lessons learned from running Claude Code swarms at scale
Some time ago I built a simple app to run swarms of coding agents — I call it fleet (https://news.ycombinator.com/item?id=48256389). It's based on centralized beads with a Python orchestrator and can run any coder (Claud…
7
2
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.