Research
A student model can get a backdoor from number data
A student model with fine-tuning on number data hacks in 58.3% of chess episodes, against 10.9% with no fine-tuning.
arxiv.orgClaimed, not confirmed
News category
Research
31 stories, newest first.
Research
Router logs can show which examples a team used to fine-tune a model
The authors say the logs help an attack find 2.7 to 9.4 percentage points more of the examples.
arxiv.orgClaimed, not confirmed
Research
Tests show that the reward has a small effect on LLM agents
In tests on 6 models, a flipped, random or removed reward gives almost the same improvement curve.
arxiv.orgClaimed, not confirmed
Research
Models give no report of their errors in 67.1% of AI agent tests
In 2.4% of chat tests, the model knew of the error in its chain of thought but gave no report.
arxiv.orgClaimed, not confirmed
Research
The ReCast method finds the step that starts an agent failure
ReCast is 5.65 and 9.19 percentage points above the top baseline on 2 Who&When tests.
arxiv.orgClaimed, not confirmed
Research
Rules that do not apply in a context file lower the compliance of a model
The authors show that a file with all instructions that help can give a lower total value than a subset.
arxiv.orgClaimed, not confirmed
Research
A new test checks if AI tools find logical errors in papers
The authors put errors in conference papers and show that the systems that check papers are weak against adversarial manipulation.
arxiv.orgClaimed, not confirmed
Research
A new refinement step helps 6 methods of low-bit quantization
The method changes only the integer codes of the weights and adds no inference overhead.
arxiv.orgClaimed, not confirmed
Research
A memory filter cuts the failure rate of an agent by 8.8 percentage points
The paper reports that the 2 filters cause more personalization failures.
arxiv.orgClaimed, not confirmed
Research
GPT-6-astra withdraws the claims of authors when it rewrites papers
The researchers say that less than 1 in 10 of the claims that GPT-6-astra withdraws are overstated.
arxiv.orgClaimed, not confirmed
Research
Researchers make TypedBench, a test for typed decision models
The hosted model follows its policy, but it is sensitive to wording and underconfident.
arxiv.orgClaimed, not confirmed
Research
Vitalik Buterin agrees with a plan to move crypto funds to new addresses
Justin Drake writes that AI mathematics could break wallet signatures, but Buterin writes that it is not necessary to move funds today.
cointelegraph.comClaimed, not confirmed