GPT-5.1 is now available for developers
GPT-5.1 is now available through the OpenAI API, bringing faster adaptive reasoning, extended prompt caching, and stronger coding performance. Two new tools, apply_patch and shell, enable coding agent…
GPT-5.1 is now available through the OpenAI API, bringing faster adaptive reasoning, extended prompt caching, and stronger coding performance. Two new tools, apply_patch and shell, enable coding agent…
The quiz teaches test-first AI development: define contracts, harden tests, fence them off, and review diffs so agents produce trusted code.
Google DeepMind used AlphaProof Code with Gemini agents to formally verify parts of Signal encryption, flagging only 1% for human review.
Gemini 4 Carbon is a slower, costlier reasoning model than Argon, best for complex, high-stakes, multimodal tasks and tunable via Python API keys.
SparseRead previews files, lets agents request relevant sections, and cuts token use up to 92.9% across tasks, making long-log debugging cheaper.
Granite 4.1 LLMON preview models use LLM-native markup to separate prompt instructions, reducing injection risk while maintaining capability.
Issue #151 covers AI memory, tool recovery, unlearning, feedback, and topology: what systems should keep, restore, or forget without harm.
A decision-first model can review AI agent tool calls before actions, reducing risk without adding another LLM's cost, latency, or uncertainty.
MIT built an AI copilot for topology optimization that lets designers give early feedback, improving manufacturability and buckling load by 39 percent
Evidence-guided recovery helps AI agents resume safely after ambiguous tool timeouts by using evidence to separate safe stopping from goal completion.
Synapsis AI uses NVIDIA GPUs to review decades of patient records inside hospital firewalls, flag care needs, and save clinician time.
NESTONE trains one LLM with early exits and shared layers, letting decisions stop at needed depth and cut compute while keeping accuracy.
Anthropic cut Claude Fable 5.2 API prices and sped replies; Mythos is restricted, and Google opened Gemini 4 to developers.
AI bug scanning can produce many Linux kernel reports, but human maintainers struggle to review them, creating a patch bottleneck and burnout.
This tutorial explains how to implement binary search in Python using recursive and iterative methods, the bisect module, and careful debugging. It also describes how to use a large Internet Movie Dat…
AI coding agents need live desktop input, so testing moved to spare laptops. This frees the main PC and requires transfer of project environments.
AAArena tests AI agents using fixed models to improve game code. Opus5.5 with Claude Code wins six gold medals but misses six leaderboards.
DataVista evaluates 19 multimodal LLMs on 961 data videos, showing top models lag human experts in narrative reasoning.
Google Deep Review is an agentic AI tool that checks long documents for logic, math, facts, and prior work, launched after a large pilot with privacy.
Microsoft Research Focus #98 reviews AI translation, a solved geometry conjecture, coding-agent costs, and a 104-language tokenizer.