Human contestants in the ICPC final get to use a computer https://
icpc.global/worldfinals/ru
les
…
@simonw
-
ICPC World Finals: Human Programmers Compete with Computer Access
By
–
-
Lethal Trifecta Attack: Blocking Data Exfiltration Strategy
By
–
I'd categorize this one as a lethal trifecta attack, especially as their solution is to cut off one of the legs of the trifecta (the ability to exfiltrate data to external attackers)
-
Salesforce Enforces Trusted URL Allowlists for Agentforce
By
–
And details of the Salesforce fix: "Starting September 8, 2025, Salesforce will begin enforcement of Trusted URL allowlists for Agentforce and Einstein Generative AI agents" https://
help.salesforce.com/s/articleView?
id=005135034&type=1
… -
Salesforce Agentforce Prompt Injection Vulnerability Fixed
By
–
Classic prompt injection exfiltration attack here, reported against Salesforce Agentforce and now fixed
-
MLX Addresses Single Prompt Execution Limitation
By
–
"You can usually run only one prompt at a time" There's been some very recent work on MLX that addresses that limitation
-
OpenAI Deep Research Tool Transparency and System Prompt Access
By
–
I would use OpenAI Deep Research (and equivalent products from other labs) a whole lot more if I'd seen the full list of tools that are available to them – and ideally their system prompts as well but that's less valuable to me than the tool definitions
-
OpenAI Models Solve Programming Challenges With Code Sandbox
By
–
Confirmation from Ahmed El-Kishky – who worked on this project at OpenAI – that their models solved the programming challenges with a code execution sandbox but no internet access
-
OpenAI Python Library Update Delayed Rollout Status
By
–
I'm not sure this has fully rolled out yet – Python library hasn't been updated since two days ago https://
github.com/openai/openai-
python/commits/main/
… -
OpenAI reasoning system answer selection without test-time harness
By
–
OpenAI say "the reasoning system selected which answers to submit with no bespoke test-time harness whatsoever" – but were the answers themselves developed with the assistance of tools?
-
Gemini Achieves Gold in Programming Contest: Tool Usage Clarification Needed
By
–
The Gemini post mentions tools in the context of training the model itself, but doesn't clarify tools were used by the model at inference time during the competition https://
deepmind.google/discover/blog/
gemini-achieves-gold-level-performance-at-the-international-collegiate-programming-contest-world-finals/
…