doyaken.ai

Hacker News Claude Code · October 12, 2026 13:52

GitHub - Oqura-ai/optim-jev: Jev based decision tools for claude code

Jev based decision tools for claude code. Contribute to Oqura-ai/optim-jev development by creating an account on GitHub.

Topics: Code Assistants

Entities: Code AssistantsClaudeClaude Code

Planet AI Developer Filter · October 12, 2026 13:01

Release b11572 · ggml-org/llama.cpp

LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.

Planet AI Developer Filter · October 12, 2026 13:00

SubQ Snap: A 384K-Context Decision Model, Price and Scores

SubQ Snap reads up to 384K tokens per decision at $0.05 per million input tokens. Its scores against Jev, the price field, and what is unverified.

Planet AI Developer Filter · October 12, 2026 13:00

Muse Wonder: Meta's Frontier Model, Price and Benchmarks

Meta's Muse Wonder costs what Claude Opus 5.5 costs, $4 in and $20 out per million tokens. On Meta's own table it leads 7 of 14 rows; Opus leads 6.

Entities: ClaudeClaude Opus

Planet AI Developer Filter · October 12, 2026 13:00

GLM-Legal: Z.ai's Legal Model, Benchmarks Checked, Price

Z.ai's GLM-Legal scores 19.2% on Harvey's legal agent benchmark. We checked it against the Vals leaderboard: sixth place, at $0.15 per task.

Planet AI Developer Filter · October 12, 2026 13:00

Harness Learning: AI Agents That Rewrite Their Own Harness

A paper trains a small model to rewrite an agent's harness from feedback; Musk compared it to Tesla FSD. What it shows and what it does not.

Planet AI Developer Filter · October 12, 2026 12:30

We Specified an AI Agent in 2016. We Called It Analytics.

Re-reading my own IBM patent on real-time concert feedback as what it actually was: an agentic loop with multimodal perception, memory-grounded inference, and a human in the loop. What it got right, and what a decade of hindsight teaches agent builders today.