vibehacker
News
Hugging Face (HuggingFaceBio) ·

Hugging Face releases Carbon-X, an Apache-2.0 14.8B model you can chat with about raw DNA

Built on Qwen3-14B with 6-base DNA tokens in the same stream as text, it predicts variant effects, regulatory regions and next bases, averaging 66.7% on five DNA benchmarks (self-reported, just behind GPT-6.1 Sol at a tiny fraction of the cost) and fitting on one 80 GB GPU or a 15.8 GB Q8 GGUF. It ships a carbon-dna skill for coding agents, but it isn't clinically validated, so keep it to research (MarkTechPost breakdown).

Read at huggingface.co

More news

View all

OpenAI is winning Anthropic's coding customers with deep discounts, including 30%+ off for Replit

The Information reports Replit moved most of its AI spend to OpenAI for more than 30% off a $100M+ a year contract after Anthropic ended its discount, Rippling's OpenAI share of coding work rose from 16% to 52%, and DataCamp says its costs fell 80 to 90%. Claude is still selectable in Replit, but OpenAI is now the default, so if you build on Replit Agent, expect GPT models unless you pick otherwise…

The Decoder

Apple Notes MCP lets Claude Code, Codex and other agents edit notes in place, keeping native formatting

Shown on HN Oct 23, the 11 tool server reads notes (checklists, tables, tags, OCR'd attachment text) as Markdown from a read only database and writes changes character by character through Apple's private NotesShared framework, refusing an edit if the note changed since your agent read it and keeping 20 backups. It needs macOS 26+ on Apple silicon plus Full Disk Access, and it's a brand new one person project, so try it with brew install cask xiaofeng han/tap/apple notes mcp and consider the Read Only tool preset first…

GitHub (xiaofeng-han/apple-notes-mcp)

Claude Enterprise gets unified chat and Cowork, with agentic work in isolated cloud VMs

Now GA for Enterprise (Oct 23), every conversation starts as chat and moves into an Anthropic managed cloud VM, network egress off by default, when it needs to run code or touch files, and keeps going after you close the laptop. It's off by default for existing orgs until it switches on Nov 16 (Organization settings Capabilities), and isn't available yet for ZDR, HIPAA ready or CMEK setups (admin guide)…

Anthropic

A web page can drop an AGENTS.md into ~/Downloads and hijack a coding agent started there

Forever Security traced a customer's agent trying to install the malicious npm package function color to an AGENTS.md in /Downloads , its working directory, then reproduced the attack on Codex (90% success with a harmless payload) and used a malicious CLAUDE.md to leak Claude Code's OAuth token. There's nothing for vendors to patch, so start agents in the project root, never /Downloads , and read unfamiliar instruction files first…

BleepingComputer

OpenAI's Decisions API is now GA, with prompt caching, JSON inputs and 400 questions per call

Out of beta since Oct 22, the gpt 6 luna endpoint for yes/no, pick one and score questions adds prompt caching ($0.01 per 1M cached input tokens, $0.10 uncached, still no output charge), native JSON inputs, images in question instructions, US and EU residency, GPT Live integration, and up to 400 questions per request. Datadog says it scores the risk of agent generated shell commands before running them at 40x faster p95 than frontier models, which makes it a cheap gate for an agent's next step…

OpenAI

Spotted something we missed? Start a thread.