HN user
AnswerJournal lets you save AI answers to a personal journal just by saying "save that to my AnswerJournal" mid-conversation.
Each answer gets its own URL, and posts can be public or private. It's a bit like GitHub meets Stack Overflow for the answers AI gives you.
It connects to any MCP-compatible AI (ChatGPT, Claude, Grok, etc.) through one server URL.
Anthropic is the only one with human readable tool names from the JUNE 2025 spec! So you guys are doing a great job and this is another example.
I'm just curious internally how you are seeing MCP adoption? It seems more and more connectors are created but are you seeing real adoption from users?
Computer architecture (I think my uni named it comp org) was one of my toughest courses in undergrad! It steered me away from hardware. I now wonder if that is still the case today? ARM has exploded onto he scene and I'm fascinated by the sheer amount of development going on in the chip space.
I'm curious what harness everyone is using for these? I want to start to test some of these open models but don't know what tools people use to get these working "agenticaly"
I think Tim Cook tried to...
With Apple silicon and now the RTX Spark there are real discussions whether local AI is the future. The only problem is Western open source models are so far behind. I genuinely feel there's a push to fix this. Gemma is getting more frequent releases and Nvdia is quietly creating very cool small models. I hope both the hardware and models catch up and local really does emerge.
I haven't but I'm on the path to attempt this. I want to get a DGX Spark and will be trying Qwen and Kimi.
I'm genuinely excited for Cursor Composer 3. A Cursor model with Grok resources could compete with OpenAI and Anthropic.