272 results on this page · clear filters

ai Sep 07 Easy Local Copilot with VS Code and Lemonade GitHub Copilot's rising subscription costs have pushed some developers to look for alternatives that keep their code local and their wallets intact. A recent guide demonstrates how to wire up VS Code's built-in Copilot chat interf... ai Sep 07 Ask HN: Best sentence corpora with native audio for language learning? A language learning community member is sounding the alarm about Glossika, one of the most popular tools for mass-sentence language acquisition, and the search for alternatives is exposing a gap in the market for structured, audio... ai Sep 07 Tracarbon: Track GPU power and carbon emissions while running local LLMs As local language models grow larger and developers run them on increasingly powerful hardware, the energy cost of inference has become a measurable concern. Tracarbon, an open-source Python library, gives developers a way to trac... ai Sep 07 Is your LLM Biased? Making ChatGPT evaluate itself When you ask a language model to estimate the probability that a remote worker is slacking off, the answer you get may depend on whether you said "he" or "she." A recent experiment tested ChatGPT with a simple workplace scenario,... ai Sep 07 Show HN: A video editor where the LLM never watches the video Most AI video editors work by feeding frames to a language model and hoping it picks good cut points. i-hate-editing takes the opposite approach: the LLM never sees the video. Audio drives every decision, scripts handle the mechan... ai Sep 07 Show HN: How Pagecord Uses AI A developer who builds a product called Pagecord using coding LLMs has published a public disclosure page detailing exactly how AI is involved in the product's development. The move came after receiving unexpected pushback on soci... ai Sep 07 The function of LLM-based math "proofs" The AI industry has been promoting language models that produce mathematical proofs as evidence of growing intelligence. A closer look at what these systems actually produce, and why the industry is investing in this particular us... ai Sep 07 Ask HN: Are agent orchestrators an anti-pattern? A question on Hacker News is pushing at a nerve in the AI agent community: are the orchestration layers that sit between language models and the tools they call actually making things worse, not better? What an agent orchestrator... ai Sep 07 Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation Zhou Yu, co-founder of Arklex AI and a professor at Columbia University, has a blunt assessment of the AI agent landscape: 95 percent of agents remain stuck in demo mode. They are impressive in controlled settings, but they cannot... ai Sep 07 10-task GLM 5.3 harness bench: Claude, OpenCode, pi, zcode, Hermes and 3code A developer running independent benchmarks on AI coding harnesses has published results that show wide disparities in how different tools use tokens to solve the same problems. The test, conducted on GLM 5.3 using ten SWE-bench ve...