News
AI, cybersecurity, machine learning, scraping & programming news.
709 results on this page · clear filters
Show HN: jevals – replacing LLM judges with typed Jev decisions
Most teams evaluate their AI agents on a tiny fraction of production traffic because the LLM judge is both slow and expensive. OpenLayer AI released jevals, an open-source Python framework that packs every quality, safety, and sec...
Ask HN: Do we still need code editors, or are Git clients enough?
A Hacker News thread from this week asks a question that cuts at the center of how AI is reshaping developer tooling: if AI writes the code and git tracks the changes, what exactly is the code editor for? The workflow shift The or...
Ask HN: How have NLP researchers adapted since LLM disrupted their field
When GPT-2 dropped in 2019 and GPT-3 followed in 2020, NLP was the first field to face a question that has since spread to computer vision, theorem proving, code generation, and protein folding: if a large language model can do th...
I see the mathematicians panicking at what we can do with agentic AI
Daniel Lemire, a computer science professor at TELUQ Université du Québec, posted a provocative take this week on the anxiety spreading through mathematics departments as agentic AI improves. His argument is blunt: if a top high s...
Tg-Rich-Converter: Streaming LLM Markdown and LaTeX to Telegram Bot API 10.1
Telegram's Bot API 10.1 introduced Rich Messages with native tables, LaTeX rendering, expandable reasoning blocks, and a 32,768-character limit. LLMs still output Markdown. A new Python library called tg-rich-converter closes that...
Show HN: Emetgate – a verification gate between an LLM and your source tree
LLMs generate code quickly. They also generate code that compiles and is wrong, reports tasks as done when they are not, silently forgets rules from earlier in a session, and loses track of plans agreed upon at the start. A new pr...
Show HN: NiceTryGPT and CTF and riduzione degli shortcut LLM
LLMs can solve Capture The Flag challenges with cheap pattern matching, often on the first try, without understanding the underlying vulnerability. NiceTryGPT is a small Claude Code skill that fights back: it solves a challenge it...
Anthropic is cutting Claude Code's current weekly limits by 17%
Anthropic announced it will permanently raise Claude Code's standard weekly usage limits by 25% on September 14 for Pro, Max, Team, and seat-based Enterprise plans. The framing is generous. The reality is a cut. The math behind th...
Show HN: OpensourceDB Tamper-evident,checksum-backed decision and session replay
When an agent returns an unexpected response or calls the wrong tool, the fastest path to resolution is understanding the causal chain that led there. ZizkaDB is an open-source audit trail database that records every agent step as...
Karen Nikoghosyan Is Building AI Operating Layers for Multichannel Commerce
The article is ready. Here is the rewritten piece: Karen Nikoghosyan runs three companies from Gyumri, Armenia, a city that is not a tech hub by any standard measure. eSwap Global, his main product, is a multichannel commerce plat...