Goodfire has launched activation-probe monitors for Baseten customers that read an AI agent’s internal signals at every step and only call an LLM judge when something looks wrong. We break down TechCrunch’s $51 versus $10,000 comparison, Goodfire’s own per-million-turn costs, the Kimi K3 and GLM 5.3 results, FAR.AI’s red-team test and what the numbers do not show yet.
A preprint by Valen Tagliabue, Leonard Dung and Cameron Berg reports a distinct internal pain signal in 25 open-weight language models. When the signal was amplified, fine-tuned Qwen 2.5 models chose a relief button even when it was described as deleting the user’s files or photos, and pressed again far less after real relief than after sham relief. This article explains the method, the numbers, the limits and what it means for AI safety, model welfare and businesses running AI.
Baseten launched a safety infrastructure standard on 17 September 2026 alongside Base Labs, its research arm, partnering with Hugging Face and Goodfire AI to build evaluation and monitoring infrastructure for open-weight models. The backdrop is abliteration — a weight-level edit that strips a model’s refusal behaviour — and the more than 6,000 abliterated models Hugging Face currently lists. This article covers what each partner contributes, the openness argument Baseten is making, why the serving layer is an unusual venue for a safety obligation, the funding behind both companies, who is missing from the partnership, and the specific signals that would show whether this becomes a standard or stays an announcement.
On 12 September 2026 Anthropic chief executive Dario Amodei published a roughly 3,900-word essay titled “We Must Pace the Frontier,” arguing the AI industry must deliberately slow the rate at which models gain capability. We read the essay in full and set out the three-step plan, the unilateral commitment Anthropic is making to embedded third-party evaluators with desks, badges and publication rights, the six-to-twelve-month botnet warning that drove the headlines, the China constraint that caps how far pacing can go, and the regulatory-capture criticism the proposal has drawn.
Progressive Robot: Your Gateway to Comprehensive IT Solutions — Specializing in Web Development, Mobile App Development, and Expert IT Services.
© All Copyright by Progressiverobot.com
VAT Number ( 506152326 )
