HackerTrans
TopNewTrendsCommentsPastAskShowJobs

talking_penguin

no profile record

Submissions

Basho's Haiku Volume One

thehaikufoundation.org
1 points·by talking_penguin·il y a 5 mois·1 comments

comments

talking_penguin
·il y a 4 mois·discuss
How is this any different from Ollama plus Open Web UI?
talking_penguin
·il y a 5 mois·discuss
Toshiharu Oseko’s Basho’s Haiku: Literal Translations for Those Who Wish to Read the Original Japanese Text is an unusual and invaluable book. It is not a Basho anthology in the usual sense, but a pedagogical work that brings together Japanese texts, literal English translations, grammatical analysis, cultural context, and philosophical background. First published in 1990, it reflects Oseko’s dual expertise as a long-time haiku student and as an interpreter of Japanese literature for international readers.
talking_penguin
·il y a 8 mois·discuss
Ha, we'll take it! It's definitely ambitious - we're essentially building a full remote desktop streaming stack on top of an AI stack on private data.

The 'madness' part is probably the part where we said 'let's do hardware-accelerated H.264 encoding and real-time agent control and make it all work with sub-100ms latency.' We think the problem space is worth the complexity.
talking_penguin
·il y a 8 mois·discuss
You're right. Monitoring is critical for this. You need to know exactly what changed and why.

This is actually where streaming + the actual architecture behing this becomes valuable beyond just "letting users watch." In Helix, every agent interaction is persisted with timing data (DurationMs), tool calls, error states, and even user feedback (thumbs up/down). Sessions track the full conversation history bidirectionally, so you can reconstruct exactly what the agent saw and did at each step.
talking_penguin
·il y a 8 mois·discuss
The streaming architecture is designed for exactly this - we originally built it for autonomous agents that need persistent development environments. The missing pieces are mostly integration work (mapping Claude's tool use format to our desktop APIs). Would be very interested to hear if others are working on similar integrations - the combination of LLM coding agents + real desktop environments feels like it unlocks a lot of interesting workflows.