Fresh stories
Ivan Leo uses Antigravity to build a bank transaction-export CLI
Ivan Leo describes using Antigravity browser automation to inspect bank websites and generate a transaction-export CLI. His custom extension works with 1Password for Singapore banks unsupported by Plaid.
Practitioners turn agent feedback into reusable skill documents and lints
Practitioners describe converting feedback into persistent skill documents and generated lints. Daily transcript reviews and execution traces also inform changes to their agent harnesses.
Gergely Orosz reports Codex blocked X accounts outside his supplied list
Gergely Orosz says Codex silently blocked X accounts that were not on his supplied blocklist. He identified the model as GPT-6.1 Sol Medium and shared his prompt to document the intended scope.
Ivan Leo uses Antigravity to build a bank transaction-export CLI
Ivan Leo describes using Antigravity browser automation to inspect bank websites and generate a transaction-export CLI. His custom extension works with 1Password for Singapore banks unsupported by Plaid.
Artificial Analysis updates Decision Index v2 with confidence-aware scoring
Artificial Analysis's Decision Index v2 adds confidence-aware scoring and raises private-dataset coverage to 45%. Its AA-Paperclip test requires all 15 answers for a document to be correct.
Hermes Agent releases a security plugin with exploitability checks
Hermes Agent's official security plugin maps attack surfaces and reviews code with parallel subagents. Optional reproduction tests run in a temporary repository copy to check whether findings are exploitable.
Practitioners turn agent feedback into reusable skill documents and lints
Practitioners describe converting feedback into persistent skill documents and generated lints. Daily transcript reviews and execution traces also inform changes to their agent harnesses.
Theo reports Opus generates unusable MCP authentication flows
Theo reports that Opus repeatedly proposes MCP authentication flows that fail on remote machines or require manual handoffs. A later guide draft also presented an MCP endpoint as a user-facing sign-in link.
Codex users report conflicting results on long-running autonomous tasks
BEBischof reports that Astra and Sol stop before completing multi-step work in Codex. Another user describes six-hour runs using permission rules, verification skills and subagents.
Top storiesthis week
Nous releases Arete-27B with an 803-prompt alignment evaluation
Nous released Qwen-based Arete-27B, training data and an 803-prompt evaluation. It reports cutting its measured propaganda rate from 22% to 1% without a significant Hermes Bench drop.
OpenAI says Codex Pro plans remove five-hour usage limits
OpenAI says Pro 100, 200 and 500 offer 10×, 20× and 50× Plus usage without five-hour limits. It also says allowances doubled for Pro plans and Business 100.
Gergely Orosz builds publication search with Codex in under 30 minutes
Gergely Orosz reports building search with Codex and turbopuffer in under 30 minutes of hands-on work. Indexing 600 articles took under a minute, with Jev reranking full-text results.
MaxxBench tests coding models on altered DeepSWE requirements
MaxxBench changes details such as filename casing and timestamp formats in DeepSWE tasks. Critics dispute whether failures establish memorization, citing task selection and unclear failure labels.
ReproBridge paper reports experiment reproduction rising to 92.6%
A summary of Google’s ReproBridge paper reports reproduction success rising from 76.4% to 92.6%, with API spending down 19.7%. It packages code, environments and launch scripts for coding agents.