LM Studio built a judge for AI commands. Then the judge started agreeing with the defendant.
A command as ordinary as git diff can become a problem for an AI coding agent once a variable gets The post LM Studio built a judge for AI commands.…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Aider, Claude Code, and OpenClaw ran an identical model. Token use varied 70-fold.
When teams price an AI coding agent, they tend to scrutinize the model. But three recent benchmarking efforts suggest the The post Aider, Claude Cod…
Replit’s new default: Auto mode picks the best model for each task
AI coding company Replit is throwing its weight behind the model-routing trend by making its “intelligent model routing” system the The…
“Posterity will find it ludicrous”: Sai agent hits 73% on OSWorld 2.0 performing routine (but necessary) work
Sai, a computer agent built by Simular, has achieved a 73% success rate on OSWorld 2.0, in a benchmark update The post “Posterity will find it ludic…
Anthropic’s Claude now has a browser of its own
Anthropic is giving Claude its own browser. As the company announced on Wednesday, Claude on the desktop (Mac, Windows, and The post Anthropic’…
OpenAI’s Astra can do a researcher’s week of work. That’s the problem.
OpenAI’s unreleased foundation model, codenamed Astra, is already working directly inside the company’s internal codebase, taking on exp…
Google’s new legal AI exposes a bigger battle over the enterprise stack
Google Cloud launched Gemini Enterprise for Legal this week, a purpose-built agentic AI solution to automate legal workflows, including contract The…
Perplexity just separated reasoning from authority. Here’s why it matters for enterprises.
Perplexity shipped Portable Computer this week, the local-first version of its Computer agent running on an Nvidia DGX Spark workstation, The post P…
Microsoft just released Agent Lightning v1.0. Here’s why it matters for platform engineers.
Agentic reinforcement learning has been suffering from a disconnect, an uncoupling, and a misarticulation. The polarity arises from how a The post M…
IBM’s new Granite 4.2 models add reasoning and stay dense
On Tuesday, IBM launched the latest family of its open-weight Granite large language models (LLMs). Weighing in at 3 billion, The post IBM’s n…
How telemetry pipelines keep AI agent costs under control
As enterprises move from experimenting with AI to running autonomous agents in production, an infrastructure problem is emerging: rising telemetry T…
Anthropic gives chat and Cowork one memory
On Tuesday, Anthropic launched a major update to how Claude remembers things. The new system combines Claude’s memory in Cowork The post Anthr…
Perplexity’s Computer agent can now run locally — if you can afford it
Perplexity, in partnership with Nvidia, has taken Computer, its agentic AI assistant, and brought it to the desktop in the The post Perplexity’s Com…
CLI or IDE? Build in verification first
The argument over where AI coding agents belong,  in an integrated development environment (IDE) or at the command line interface The post CLI…
AI agents are spreading fast. Their rules are still catching up.
AI agents are already inside the enterprise, but the rules for controlling them haven’t caught up yet. Some 86% of The post AI agents are spre…
“You can rent a feature, but you can’t rent a foundation”: why MotherDuck bought the startup already powering its data pipelines
What do you do when a technology you’ve become dependent on belongs to someone else? You buy the startup behind The post “You can rent a featu…
Junie now runs entirely offline. Can you spare a 64 GB M5 Mac?
While most AI coding tools default to cloud-hosted models, local model runtimes have become a viable alternative for developers who The post Junie n…
Grok Bot vs. Hermes: Where each draws the security boundary
Put several AI bots to work, and a mistake by one may not stay within its assigned task. For example, The post Grok Bot vs. Hermes: Where each draws…
One pull to wipe them all
Q Developer is a free extension that lets a coding agent read a project, propose changes, and run commands on The post One pull to wipe them all app…
Securing sandboxes: What happens when AI agents escape containment?
On July 16, the team at Hugging Face noticed something weird moving through their production systems: An intruder that was The post Securing sandbox…
Six identity capabilities for securing autonomous AI agents
The artificial intelligence landscape has reached a pivotal inflection point. Over the past several years, the paradigm has shifted from The post Si…
Anthropic’s new browser tool doesn’t actually run a browser
Anthropic launched a new Browser Use tool that gives Claude a structured view of a web page in addition to The post Anthropic’s new browser to…
Claude Opus 5 scored 30% on ARC-AGI-3. Wrapped in Nvidia’s AVO, it hit 100%.
Nvidia first introduced its Agentic Variation Operators (AVO) general-purpose coding agent system in late March 2026. The company has now The post C…
Most coding agent benchmarks skip large-scale refactoring. Not this one.
AI coding agents still struggle with large-scale refactoring, with the best model achieving only a 41.2% resolve rate on a The post Most coding agen…
GitHub now sees 2.9 billion commits a month — and it can’t keep up
Per month, GitHub now sees 2.9 billion commits, 130 million merged pull requests, and 24 million new repos. Back in The post GitHub now sees 2.9 bil…
Google’s AI coding agent just escaped its own IDE
When Google launched Antigravity in November 2025, it was on the premise that developers could hand an entire coding task The post Google’s AI…
Slack makes it easier to install agents built with third-party tools
Slack on Thursday rolled out Add to Slack, which lets users more easily bring the agents they’ve built with ten The post Slack makes it easier…
Warp wants to make it easier to build your software factory
On Tuesday, Warp introduced Warp Factories, open infrastructure for building cloud software factories, agentic systems that automate work across the…
Researchers hid an attack inside AES encryption. The AI model cracked it open willingly.
Security filters are designed to catch malicious instructions before an AI model can act on them. Researchers at AI security The post Researchers hi…
Slack has a new channel type — but only agents can create one
Slack on Thursday launched Slack Code, a new kind of Slack channel that’s built for coding agents and the developers The post Slack has a new…