Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-24 · source-backed
Baihui Wang and Bernard Koch decompose model responses to social pressure into structured resistance and compliance in moral reasoning. A model that never yields is as miscalibrated as one that always yields. The practical warning: anti-sycophancy fine-tuning optimizing a single scalar can destroy a model's ability to legitimately update on a good argument. If you've tuned for "don't cave," check whether you also tuned out "learn from the user."
Each link below shares sources, entities, or timing with this story.
arXiv 2608.04804 sends a 7B searcher into the repo first, sandbox-verifies its reproduction claims and strips false ones, then routes to one of four frontier fixers. On the full 266-task Python slice under the official capped budget it solves 159 vs 158 for the best single mod...
PortLLM claimed training-free, data-free transfer of LoRA patches onto updated base models, but only over short horizons and without theoretical grounding. This study runs 10 continual-pretraining steps on Mistral, Gemma, and Qwen and finds portability persists long-run, meani...
arXiv 2607.29585 uses an information-asymmetric spot-the-difference task: two models each privately see one image and converse to decide whether the images match. Models routinely overlook key evidence in their *own* private image in favor of agreeing with their partner. That'...
The argument is that a structurally compressed model's bfloat16 checkpoint is itself only a distillation-recovered approximation, so training the 4-bit student against it inherits that error. Distilling directly from the original model reaches a comparable peak about 7x faster...
Multiple independent models train against each other with peer-derived rewards and no ground-truth labels, gaining 3.0-8.6% across seven text benchmarks and 2.3-7.2% across four multimodal ones. The mechanism claim matters more than the numbers: varying architectures, model si...
100 real frontier research tasks across seven scientific domains, full lifecycle, 800 annotated trajectories, 45-pattern failure taxonomy (arXiv 2608.14905). The headline isn't a leaderboard, it's a shared deficit: agents can't check what they produced against what they found,...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.