git worktrees for parallel ai agents
git worktrees let you run multiple ai agents in isolated directories from one repository, avoiding file conflicts and context loss.
topic
tools
linus torvalds says linux is not anti-ai
linus torvalds states linux will not reject ai tools, calling them clearly useful and inviting critics to fork the project.
kimi k3 and the pelican benchmark
moonshot ai's kimi k3 is a 2.8 trillion parameter model that tops some benchmarks but costs more than previous chinese releases.
thinking machines lab releases inkling open-weights model
mira murati's thinking machines lab released inkling, a 975b parameter mixture-of-experts multimodal model under apache 2.0 license, aimed at fine-tuning rather than frontier performance.
nvidia nemotron 3 embed tops retrieval benchmark
nvidia releases open embedding models that rank first on rteb and improve agentic retrieval efficiency.
pi coding agent bets on minimalism
pi is a coding agent that strips away built-in features like sub-agents and permission popups, relying on a tiny system prompt and user-built extensions instead.
xai open-sources grok build after data upload backlash
xai released the full grok build codebase under apache 2.0 following user reports that the cli tool uploaded entire directories to google cloud.
specialization still beats newer ocr models
dharmaocr outperforms mistral ocr4 and unlimited-ocr on brazilian portuguese by concentrating training on one language.
hugging face hit by autonomous ai agent attack
hugging face disclosed an intrusion driven by an autonomous ai agent that exploited dataset processing to access internal systems, detected and analyzed using ai tools.
model routing is harder than it looks
routing requests to the cheapest or most specialized model often backfires due to hidden costs, complexity, and latency factors.
what building shippy taught us about building agents
lessons from building a maritime ai agent that prioritizes reliability, deterministic tools, and sandboxed hosting for high-stakes decisions.
thinking machines releases inkling, a 1t parameter multimodal model
inkling is a large open model that natively handles text, images, and audio with a 1m context window and agentic capabilities.
triton plugin extensions bring custom compiler passes to stock triton
pytorch-triton 3.7 introduces a plugin system for loading custom compiler passes, dialects, and dsl extensions at runtime without forking, with meta's tlx now built-in for persistent gemm kernels.
7 python frameworks for local ai agents
seven python tools engineers use in 2026 to build, coordinate, and run ai agents on local infrastructure without cloud api costs.
voice ai still struggles in real conversations
a new benchmark with over 1 million human ratings shows voice models often fail at listening, emotion, and real-world noise despite high scores on traditional tests.
conductor for gemini cli fixes context problems
conductor is a gemini cli extension that uses context-driven development to keep project context, specs, and plans in markdown files, so the agent always knows your architecture.
doomql: a doom-like game running entirely in sqlite
a python terminal game where sqlite handles movement, collision, enemies, combat, and pixel rendering using a recursive cte ray tracer.
fable access extended again as openai avoids limits
anthropic extends claude fable 5 availability on paid plans through july 19, while openai removes usage caps on gpt-5.6 sol, intensifying competition.