Artificial Intelligence

Stateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows

MarkTechPost Oct 24, 2026, 1:29 PM (1 hour ago)

Discover how to extend agentic memory beyond basic prompts by building a stateful engineering copilot with Letta. This comprehensive guide covers inspectable core memory, archival vector retrieval, multi-agent shared state, custom tools, and portable workflows.

Read the full story on MarkTechPost.

Read at source

Artificial Intelligence

UK funds £100m AI biosecurity lab with OpenAI and Anthropic

The UK government will put £100m into a new AI Biosecurity Lab, which will use advanced AI to spot and respond to biological threats. OpenAI and Anthropic will add up to £200m between them, the Cabinet Office said on Saturday.

The Next Web 1 hour ago

Artificial Intelligence

Google Says Gmail and Photos Data Shared With AI Search Could Be Used for Targeted Ads

Google has updated its privacy policy to spell out that using personalized artificial intelligence (AI) features in Search or Gemini could allow the company to serve targeted ads to users based on their activity on other connected Google services.

The Hacker News 1 hour ago

Artificial Intelligence

OpenAI cuts live internet from all frontier model training

OpenAI has cut live web access from all training of its most advanced AI models. The models now browse and search a cached copy of the web instead, the company wrote in a blog post on Friday.

The Next Web 1 hour ago

Artificial Intelligence

Check Out the Many Uncanny, Human-ish Voices From Block’s New AI Model

The model goes by Dessa. Presumably because, once you hear it talk, you’ll say “‘Dessa’ pretty convincing human voice.”

Gizmodo 1 hour ago

Artificial Intelligence

Meta is delaying its controversial new business terms amid scraping concerns

Meta drew flak for an upcoming change to its business terms that would allow it to scrape business accounts’ content for AI training.

Engadget 1 hour ago

Artificial Intelligence

What makes a fax HIPAA compliant in the AI era

HHS has never told healthcare to stop faxing. Its guidance says the Privacy Rule permits physicians to disclose PHI to another provider by fax for treatment, as long as reasonable and appropriate safeguards are in place. Take two identical referral forms sent the same morning.

The Next Web 2 hours ago

Latest from MarkTechPost

Artificial Intelligence

NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B for local voice assistants, game characters and robots, targeting about 4GB of VRAM on RTX and Jetson.

MarkTechPost 8 hours ago

Artificial Intelligence

Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms

Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders for interactive world models. World models built on CADRE run at 20 fps on 1 H100 and react in under 230 ms.

MarkTechPost 12 hours ago

Artificial Intelligence

Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context

Moonshot AI released Kimi K3.1 Pro, a 2.8T-parameter, 104B-active MoE model with 1M-token context. It scores 65.7% on Terminal-Bench 4.0, costs $2/$10 per million tokens, and open weights arrive by Nov 4, 2026.

MarkTechPost 13 hours ago

Artificial Intelligence

TinyFish Breaks Down Agentic Search Architecture for Production AI Agents

TinyFish published two engineering research articles on agentic search. One defines a 7-phase production architecture with evidence contracts and bounded retries. The other explains why its deep research system dropped a separate planner and per-query subagents.

MarkTechPost Oct 23, 2026, 11:58 AM