» Tag
llm
535 postsKimi Linear: Hybrid Attention Architecture Beats Full Attention
Kimi Linear's KDA module outperforms full attention, cutting KV cache by 75% and boosting throughput 6x at 1M context.
LoRA Speedrun: A Public Wall-Clock Leaderboard for Fine-Tuning
LoRA Speedrun is a public, verified wall-clock leaderboard for LoRA fine-tuning techniques on Qwen2.5-1.5B and GSM8K, run on a single L40S GPU.
A CRM That Changes Its Schema via Typed Tools, Not LLM-Written SQL
A Show HN CRM lets users edit database schemas via chat using typed tools instead of LLM-generated SQL, with dual validation and safe undo.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comMeasuring GEO: A Weekly Probe to Check If AI Actually Cites You
A cheap weekly probe using Perplexity Sonar checks whether AI assistants actually cite your content, turning GEO into a measurable trend.
78,000-Tweet LLM Study Debunks the Trump-Tweet Market-Mover Myth
A 78,000-tweet LLM study tests whether Trump's posts move markets — and uncovers seven statistical bugs before landing on a null result.
AI Agent Cost Drift: Rolling Dashboards Miss 0.35%/Day Creep
Why do rolling-average dashboards miss a 0.35%/day AI agent cost increase? A math proof and 60-day test show the blind spot - and the fix.
The 75% False-Negative Wall LLM Reviewers Can't Move
Why LLM-based reviewers hit a fixed 75% false-negative rate, and why voting, reruns, and prompt calibration all fail to move it.
Your AI Visibility Score Is Probably an Artifact
A 1,790-query audit finds most AI-visibility scores are artifacts, exposing why blending branded/unbranded prompts and single-engine scores mislead teams.
A Unified Framework for Self-Improving Agent Systems
A conceptual framework unifying Skill evolution, harness adaptation, and self-referential evolution in self-improving AI agent systems, beyond model weights.
LiteLLM's AI pricing table's only test is jq empty
LiteLLM's widely-reused AI pricing table is validated only by jq empty — no source checks, no dates, no history. Here's what engineers should know.