ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode
Product

AGENTS.md

2 mentions in 7 days · 3 in 30 days · 3 total · first seen · last

Search everything

Timeline

[AINews] Here are 6 Clones of Jev in 2 days

Jev's non-generative decision model launch drew 36M views and six open clones in two days, positioning discriminative models as fast complements to LLMs.

Latent Space's AI News roundup for 9/17-9/18/2026 centers on Jev, a non-generative 'System 1' decision model whose launch video hit 36M views in two days and reached roughly 13% of teams. At least six open reproductions appeared, including Bespoke Nimble (a Qwen3.5-9B LoRA fine-tune improving a curated eval from 66% to 90% versus Jev's 93%), SemIf (4B/35B Qwen3.5 backbones), and Kev-0.5B built on Qwen2.5-0.5B. Practitioners highlighted calibrated-probability use cases in routing, escalation, and browser/computer-use workflows, with Braintrust reporting ~400x lower scoring cost versus prior setups. The roundup also covers Claude Code v2.1.277 adopting the AGENTS.md standard and research showing coding-agent harness design materially shapes benchmark results.

Latent Spaceupdated · 16h agofirst · 21h agoAI industry 4 sources1

Claude Code now reads AGENTS.md if there is no Claude.md

Anthropic's Claude Code 2.1.277 adds AGENTS.md support as fallback project instructions when no CLAUDE.md exists, plus gateway proxy options and many bug fixes.

The Claude Code changelog entry for September 18, 2026 (version 2.1.277) adds AGENTS.md support: in projects without a CLAUDE.md, Claude Code now reads AGENTS.md as project instructions, changeable under /config (not yet on Bedrock, Vertex or Foundry). The release also adds CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1 for gateways whose only egress is a forward proxy, and an optional static headers map for gateway upstreams. Numerous bugs were fixed, including hanging claude -p and Agent SDK sessions, malformed customApiKeyResponses crashes, plugin install corruption, Edit tool escape-sequence mishandling, and update-check errors behind proxies.

Hacker News · AI · 1d agoAI tools & infraHN 60↑ · 26 comments1· 1 read

GPT-6 Astra needs leaner prompts and fewer guardrails, OpenAI recommends

OpenAI's Eric Provencher advises developers using GPT-6 Astra to shorten skill descriptions, trim AGENTS.md reading requirements, relax approval rules, and define clear completion goals.

OpenAI's Eric Provencher published guidance on adapting developer setups when switching to GPT-6 Astra, arguing that overly long skill descriptions, blanket reading requirements, and rigid approval rules waste context or make the agent stop too early. Skills are Markdown prompt files whose names and descriptions enter Codex's context, and too many or conflicting skills cause truncation and wrong skill selection. He recommends selective document references in AGENTS.md, explicit permissions for safe operations like local test runs, and defining upfront what "done" means, since Astra may stop earlier than GPT-5.6 Sol even without restrictions.

The Decoder · 7d agoAI tools & infra1

Appears with

product Claude Code 2ai model Claude 1ai model GPT-5.6 Sol 1ai model GPT-6 Astra 1ai model Jev 1ai model Jevlike 1ai model Kev-0.5B 1ai model Laya 1ai model Qwen2.5-0.5B 1ai model Qwen3.5-9B 1ai model SemIf 1organization Anthropic 1organization Latent Space 1organization OpenAI 1product Claude 1product Cline 1
Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.