2026 / Jan / 8

> Thursday, January 8, 2026

2 posts

@

What’s New in ICML 2026 Peer Review; ICML Blog (blog.icml.cc)

ICML published some new rules for their 2026 peer review. Most notable are measures to combat AI slop and other ways of peer review abuse. They also mandate participating in organization of the conference if you submit at least four papers. Also, they will provide “advanced reasoning” LLM feedback before the submission deadline for authors.

It is clear that AI is causing stark changes in the research landscape. Right now it’s focused on AI slop, peer-review abuse, and so on. But I believe this is only the beginning, and we will have to deal with the broader impact of AI upending research as it was before.

Running Claude Code Non-Interactively

You can easily run claude code on a subscription non-interactively. First create an OAuth token using claude setup-token. Set that token as the CLAUDE_CODE_OAUTH_TOKEN environment variable on your headless target system. Finally, run claude non-interactively with claude -p "prompt". Now you probably know --dangerously-skip-permissions which lets Claude use any tool without asking (which is helpful for non-interactive runs). By default, it will only output something in the very end. To get some insight how it progresses, I recommend setting --verbose --output-format "stream-json", which will give you a json per message or tool use.

{"type":"assistant","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01VCMSqhZxoZQ6nqWGcA5Myd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MNxKniNF9LWBGrZh5ppuRF","name":"TodoWrite","input":{"todos":[{"content":"Evaluate Stage 3.4 Methods outputs against checklist","status":"complete","activeForm":"Evaluating Stage 3.4 Methods outputs against checklist"},{"content":"Create improvement tasks for any checklist failures","status":"in_progress","activeForm":"Creating improvement tasks for any checklist failures"},{"content":"Post detailed Linear comment with findings","status":"pending","activeForm":"Posting detailed Linear comment with findings"}]}}],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":244,"cache_read_input_tokens":87250,"cache_creation":{"ephemeral_5m_input_tokens":244,"ephemeral_1h_input_tokens":0},"output_tokens":637,"service_tier":"standard"},"context_management":null},"parent_tool_use_id":null,"session_id":"a23ce490-1693-496b-ad08-8e082248416d","uuid":"8620af06-c8e7-4409-9b91-a2248e353ecf"}

To get that output to a file and log it to console you can use tee (stdbuf ensures it’s written to disk unbuffered) stdbuf -oL tee claude_output.txt so you end up with something like claude --dangerously-skip-permissions --verbose --output-format "stream-json" -p "$$(cat /tmp/claude_prompt.txt)" | stdbuf -oL claude_output.txt