Search: “chat”

We're sharing progress on ChatGPT for Teens, our ChatGPT experience for people under 18, alongside a preview of College Planner, new study tools, and support for college advisers and teen voices. Chat

Ben Affleck reveals he writes Python, understands convolutional neural networks, worked extensively with GPUs, and used his celebrity status to get private looks at Google and OpenAI’s video models “I

GPT‑6 with Intelligent UI rolls out globally to Plus, Pro, Business, and Enterprise users today and will expand to Free and Go users starting tomorrow. GPT‑6 in ChatGPT is powered by GPT‑6 Sol for Plu

OpenAI introduced interactive in‑chat tools that let users play games or run utility calculators—such as an interactive budget planner—directly within a conversation. The demonstration, released on Oc

New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,

After much testing and talking to actual users across all three proactive AI agents: Muse - best one for your parents, heavy IG/FB users, people who like or need easy setups, people who don’t want to

With Instinct, my Google usage has dropped 90%. And before you all complain in the comments, if you leave the X sphere, you’d hear most people still use Google too. I continued to use traditional sear

GPT-6 Astra Pro in ChatGPT got an upgrade with faster responses and improved use of plugins and tools. And now, multiple agents can tackle different parts of a task in parallel. You can follow each ag

We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the harnesses, no changes to the training code. Any open model, any task set, fully o

Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinity set, above Gemini 3 Flash with browser use at 70.1%. They

New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,

If an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments be

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode

Learn to build custom harnesses, folks! Here is a highly recommended paper from Google on recursive agent harnessing. Great insights if you work on evolving your harnesses. It also offers an important

Fascinating paper from Google DeepMind. They studied a market where AI agents bid to answer each user prompt. Each agent bids its expected reward minus its inference cost. A first-price auction is sim

Banger paper from Google DeepMind on long-horizon multi-agent coding. (bookmark it) They report that, to the best of their knowledge, this is the first end-to-end autonomous completion of Minecraft by

Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline

llama.cpp now has a Windows app 🦙 Llama Windows makes it easy to run models locally, with optimizations for NVIDIA RTX Spark. 📥 Browse and download models from Hugging Face 💬 Chat with local models ri

Brilliant paper on agentic continual learning from Meta and MIT. (bookmark it) Agent memory harnesses usually only write forward. A lesson goes into the bank and is never checked against whether it he

Interesting new research from Meta Superintelligence Labs It discusses how reward hacking affects coordination in multi-agent coding systems. Coding agents on a team share code, memory, and plans, so

New work from Meta AI on agents that manage their own search. (bookmark it) A ReAct agent keeps every failed attempt in one context, making useful evidence harder to find. To improve on this, they pro

Must-read paper from Sakana AI on orchestrating coding agents for scientific research. (bookmark it) This is an important read with lots of useful insights if you are building multi-agent systems. I l

Giving my Dot a dedicated email address turned out to be surprisingly painless & solved a few problems around how to relate to a personal agent. I don't want it using my email or drafting messages on

Brilliant paper on scaling research agents from UC Berkeley. (bookmark it) They propose an unexpected and interesting way to scale automated research with agents. It's common to see research agents ke

Mistral AI has launched its Connectors API into Public Preview, enabling developers to register Model Context Protocol (MCP) connectors once and deploy them across multiple Mistral products. This 'bui

Introducing remote agents in Vibe and Mistral Medium 3.5. You can now launch remote agents in the cloud, including from the CLI or Le Chat. Plus, new Work mode in Le Chat for complex, multi-step tasks

I got early access to SpaceXAI’s new Grok @Bot template sharing feature, which lets you create custom Bot templates that other people can download and use. I created a Home Robots template that lets y

The ultimate Grok @bot set up for me is to filter EVERYTHING - absolutely everything through one agent and hide everything else. That agent is in charge of as many agents as needed that will own speci

zai earnings transcript was a really good read, a list of interesting points (mostly verbatim from the transcript): * Chat → Coding → Agent → Cowork → Autonomous AI * What truly matters is who can con

The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b

We’re building Copilot as a new OS for work that spans every model, every form factor, and every task. Today, we’re announcing our biggest update to Copilot to date, bringing four things together: · A

New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,

If an agent saves an engineer 2 hours to implement a feature but collectively costs the team 3 hours in alignment and review, the ROI is negative. Isolated chats are suboptimal in team environments be

I built a @Grok @Bot that watches SPCX on its own — fully automated, no manual work. I’ve been running it for over a month and fine-tuned it several times. This version is very good. Every weekday bef

Multimodal API support 🔌 🔹 Set model='deepseek-v4-flash-vision-exp' 🔹 Images are tokenized for billing: up to 384 tokens each, at V4-Flash pricing 🔹 Supports Chat Completions, Messages & Responses 🔹 S

Companion to the Qwen 3.8 Release Megathread. Compiled from ~2,000 posts scanned across both subs, with deep reads of the 45 highest-signal threads (560 posts and comments), Aug 15–22, 2026, plus inde

Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4 Pro coding agents - Kimi K3, DeepSeek V4 Flash, GLM 5.2 small + fast - Qwen3.8 27B, gpt-oss 20B mid-siz

Great tips on working with reasoning models. Normally you would append what the model figured out after the document and ask again. It turns out that where you put the reasoning trace changes long-con

Impressive paper showing how much the first retrieval step matters for deep research agents. It helps to improve GPT-5.5 from 83.1% to 90.5% on BrowseComp-Plus with the same retriever and the same age

Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modified harness matched Codex for 4.03. Specifically, a coding

Huge release from EverMind AI. Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates them th

Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro

Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of excitement around RL environments so this is a great read. Skill2Env

Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper shows that agreement can hide shared errors, while disagreement

Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modified harness matched Codex for 4.03. Specifically, a coding

Banger paper from NVIDIA. One exciting trend I am seeing is building verifiable environments for your agents and training the harness alongside the model. Co-evolving the harness and the model is a bi

come hear about building with open frontier models Open Haus Berlin lineup: → @RiqwanMThamir from @n8n_io → Harry Kim from @nvidia → @zainhas from Together AI good food, drinks, and better arguments a

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still

llama.cpp now has a Windows app 🦙 Llama Windows makes it easy to run models locally, with optimizations for NVIDIA RTX Spark. 📥 Browse and download models from Hugging Face 💬 Chat with local models ri

New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin