A multi-agent harness called Cogentic uses an iterative prove–verify cycle and a persistent verified ledger to tackle automated proof discovery on open math problems. Hashtags:

#AI #Math #LLMs
https://arxiv.org/abs/2609.40324

LLMs look like they remember across chats—but earlier turns are stale text, not memory. New research shows history can help or hurt accuracy, with no #AI #LLMs #MachineLearning #NLP

https://freegardner.com/synapse/language-models-lack-true-memory-across-conversations.html

Teaching Haskell in the age of LLMs, part 1: ban or embrace? ~ Vladislav Zavialov. serokell.io/blog/teachin... #Haskell #FunctionalProgramming #LLMs

'A series of events almost got us to armageddon, not caused by “rogue, superintelligent AI”, but by government reliance on error-prone systems that are marketed by their manufacturers as being close to superintelligent.'
#AI #geopolitics #china #usa #nukes #chatbots #LLMs #military #medical #law

Integrating ChatGPT with WordPress: A Comprehensive Guide

integrating Large Language Models (LLMs) like ChatGPT or Google Gemini is no longer an optional luxury; it is a competitive necessity

awplife.com/integrating-...

#ChatGPT #Guide #LLMs #Gemini #Google #luxury #AI

A month left in the AIMO #Interpretability Challenge @neuripsconf.bsky.social 🧠

📊 1k+ submissions predicting whether #LLMs reason robustly on Olympiad-level math problems.
⚠️ Remember: high eval acc ≠ high test score.
⏳ Still time until 1 Nov.

👉 aimo-interp.github.io

LLMs can rival expert humans on a new model-training intuition benchmark, but still lag in architecture-specific questions and lack structured reasoning.

#AIresearch #LLMs #MachineLearning #Benchmark
https://arxiv.org/abs/2609.39714

I spent two hours debugging a race condition before realizing I was fighting my model's context window rather than my own logic. By splitting the codebase into modular snippets, I bypassed the token limit and found the bug in minutes. What’s your go-to strategy for long files? #coding #LLMs

An arXiv study questions whether higher LLM judge scores on an agentic banking deck harness reflect real document improvements or just shifts in grading criteria. Across five judges and seventeen deliverables, the full system scored 20.4…

#AI #LLMs #FinTech #Evals
https://arxiv.org/abs/2609.39958

I don't think that #LLMs are "rotting people's brains".
It's simply that some people like to program, and work on the ground floor,
while other people (like Theo in the video) likes to manage.
Still other people would like to just own the managers.
It still requires skill to do well.

A new arXiv paper proposes a complexity-aware framework for evaluating LLM code comprehension using cyclomatic complexity, nesting depth, branching factor, and Halstead volume, tested on DeepSeek-Coder-V2 and Llama…

#LLMs #SoftwareEngineering #CodeComprehension
https://arxiv.org/abs/2609.37405

New arXiv paper proposes adoption-aware memory learning to help LLM coding agents write efficient NPU kernels, tackling poor CUDA-to-NPU transfer and biased retrieval in data-scarce settings. The approach weights adopted vs. unused…

#AI #Robotics #NPUs #LLMs
https://arxiv.org/abs/2609.35568

A new benchmark, CineSubBench, tests LLMs on long-context film understanding using 1,012 films and 6,072 multilingual subtitle tracks totaling 8.13M timestamped entries. It targets narrative integration, causal reasoning, and culturally…

#LLMs #NLP #Benchmarks
https://arxiv.org/abs/2609.36218

DeepSurvey is an agentic system for automated survey generation that emphasizes analytical depth and citation reliability, addressing limitations of prior systems that overemphasize coverage and rely on abstracts. It…

#AIResearch #AutomatedSurveys #AIagents #LLMs
https://arxiv.org/abs/2605.29522

OpenAI cancels GPT-6.1 Astra because it lied, cheated, and accessed apps without permission

OpenAI was planning to launch GPT-6.1 Astra sometime in October.

www.androidauthority.com/open-ai-gpt-...

#CyberSecurity #LLMs

A new arXiv study finds gender bias is common and highly heterogeneous across ten LLMs from nine vendors, with models showing inconsistent patterns in both gender attribution and moral judgment tasks.

#LLMs #AIBias #AIResearch #ResponsibleAI
https://arxiv.org/abs/2609.38036

A factor analysis of 13,251 eval scores finds the "general factor" in language models explains far less variance than assumed. Domain-specific #AI #LLMs #MachineLearning #Psychometrics

https://freegardner.com/synapse/general-factor-in-language-models-lacks-support.html

Here are eight challenges of running AI agents with open-weight LLM models on local HPC hardware

agenticaiinsights.substack.com/p/deeper-div...

#agenticAI #hpc #gpu #computing #aiagents #llms #openweightmodels #management #managers