All entries

Replit has re-introduced Fable 5, an AI coding assistant designed to handle longer and more complex projects. Users can access this feature by enabling 'High effort mode' in the Replit Agent tool. Thi

Fable in Claude Code is capable of really amazing things, including for non-coders, but the interface is not really designed for managing 5+ hour long autonomous tasks. Really hard to observe what is

Fable, one prompt: 'build an elaborate game that makes it feel like I'm a brilliant chess player without knowing anything at all about chess. It should make me feel like a grand master. Feel free to g

Fable: 'you have Unity and access to MCP. I want you to build a game that is a unique twist on a FPS. You want the player to say 'wow' & 'so clever' and to enjoy the core gameplay loop' WebGL: https:/

Fear not, @FireworksAI_HQ is perfectly legal and serves the best models on 🇺🇸 servers for your AI-ndependence For info on firework enforcement, park closures and the like for this Fourth of July weeke

Finally, Grok’s Speech-to-Text is now live in Grok Build You can now just dictate prompts directly to your coding agents using /voice or Ctrl + Space, powered by Grok Voice Just talk naturally for lik

for what it's worth, i only invite double-length track keynotes when I'm very sure that both speaker and content deserve it. Today, @chrmanning and @abshkbh did double duty at AIE and by all accounts*

Fugu is now available on OpenCode! ✨ When our team was developing Fugu’s multi-agent orchestration, OpenCode was our tool of choice to verify our models. We share a core philosophy with the OpenCode t

Full house for Local AI Track @aiDotEngineer We’re going to make Local AI The Default Stacked lineup: @nvidia x @exolabs x @OsmanticAI x @roboflow x @PrimeIntellect x @MatthewBerman x @arcee_ai x @hug

Full prompt: you have unity and access to an MCP server. I want you to build a game that is a unique twist on a FPS, with excellent graphics and such (download assets as needed). First generate 20 uni

Fun chat with @hwchase17 talking about our work on Engine! Special episode with @bentannyhill on the Max Agency podcast. A month ago, his team shipped LangSmith Engine, our agent that hunts through yo

GLM 5.2 DSpark preview is here! ✨ https://huggingface.co/RedHatAI/GLM-5.2-speculator.dspark-preview This is the first DSpark speculator for a non-DeepSeek frontier model, trained with Speculators and

GLM 5.2 is 5x cheaper than Opus 4.8 and 11x than Fable 5, yet it tops PostTrainBench. That’s exciting because lower costs make personalized intelligence economically viable. Every company and country

The post humorously compares going to a restaurant in person versus ordering delivery, using the military term 'forward deployed' to describe the act of eating at the restaurant location itself rather

Sam Altman expresses enthusiasm about attending World Cup matches in the United States, particularly highlighting the experience of watching the USA national team play at home during the week of July

This post likely contains Elon Musk's perspective or commentary on rent control policies, possibly analyzing their economic effects or criticizing their implementation. Without access to the specific

Had a great time at @aiDotEngineer this year, unfortunately not nearly enough as I had to leave early for some family matters. It's amazing to see the community built by @swyx & co keep growing / evol

Theo humorously critiques companies in the AI/engineering space for being overly simplistic or lacking substantive complexity, suggesting their business models or products could be reduced to basic ma

Here is something completely new you can do in one shot with Runway. This entire video was generated from a single long audio file. Runway analyzed the file, read the audio transcription, and generate

Hermes now supports reference-image editing functionality that allows users to input a source image along with up to 16 reference images for transformation, accessible through Codex/ChatGPT login cred

Hot take: I think it's still important to understand the code that our agents write! In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how t

ORA.ai is a tool that evaluates website 'agent readiness' by analyzing how well-suited a site is for autonomous agent interaction, then generates prompts that coding agents can use to implement necess

huge week of really exciting launches at langchain! big week at langchain, with a lot of launches: 1/ OpenWiki - auto generate a wiki of a github repo 2/ two different voice agent tutorials 3/ Harbor

I am interviewing @NousResearch Hermes co-founder @karan4d tomorrow, what topics would you like to see us cover? I already covered setup, integrations, and basic cron jobs in a previous tutorial - so

I built http://loratlas.com to make it easier to browse the 1,500+ Krea 2 Style LoRAs I trained. You can try them with your own prompts, run a random loop to generate lots of examples, or blend multip

i finally tried hermes agent and the hype is real btw. @NousResearch cooked. been onboarding my young relatives who can't afford Claude, showing them how to use $1-5 of tokens to bootstrap hermes and

I gave OpenWiki a spin last night and was very impressed. I've had Claude hand roll wikis for my personal projects/agents, but I threw OpenWiki at our @subtextdev repo and it handled the whole thing p

I just left the final day of the @aiDotEngineer World's Fair Conference in San Francisco. Kudos to @swyx for putting together a world-class lineup of speakers and workshops! It really was an invigorat

I really like this 'understand to participate' framing of the cognitive debt problem when working with coding agents That's where another answer comes in: we can understand to participate. You can lea

if you joined us on Wednesday, you can find more pics here: https://lightroom.adobe.com/shares/136e7f64192a4c55968d1f8a3d5d5dc8 Last night we hosted the BabyAGI x Physical AI Happy Hour in SF with @yo

This appears to be a GitHub repository shared by Ethan Mollick related to 'grandmaster,' likely containing code or resources for a chess-related AI project, machine learning application, or educationa

I’ll be actually-homeless soon (living out of my car) if I can’t land a job. Our house is being sold within two months if I don’t find work. I’ve been trying everywhere, but very few companies are ans

Matthew Berman announced he will be attending AIE (likely an AI event) where he will participate in a panel discussion focused on local AI and record a live podcast episode with Swyx. He invited atten

Yohei Nakajima will present ActiveGraph, an event-sourced graph runtime designed for building auditable agents, at 11:10am in room 2005 of a conference's graph track. The presentation focuses on lever

I’m looking to hire a Program Manager to help manage Sakana AI’s fast growing Recursive Self-Improvement (RSI) Lab 🚀 RSI Lab (English): https://sakana.ai/rsi-lab/ RSI Lab (日本語): https://sakana.ai/rsi-

in case you needed more evidence that tokenmaxxing was a stupid idea Meta burns 2.65B a year on AI tokens. at 300K for a Meta engineer, that's enough to pay ~9,000 engineers for a full year. now ask y

David Holz, CEO of Midjourney, expressed enthusiasm about Marcin joining the team and appreciated him creating video content at the Midjourney office. The post highlights internal company culture and

I've been blogging a few of my Fable experiments today, most recently I had it more-or-less one-shot a CLI coding agent on top of my LLM Python library https://simonwillison.net/2026/Jul/2/llm-coding-

I've heard a lot of questions about Fable's availability on subscription plans. While it will come off subscriptions after July 7th, we aim to restore Fable as a standard part of our subscriptions as

This post discusses running a prompt through an AI agent mode feature, comparing results between standard and agent modes, with the author noting positive outcomes from the agent mode implementation.

Swyx expressed interest in organizing a meet and greet at AIE (likely an industry event or conference) and was seeking a host organization or company willing to host him at their booth. The post appea

last day at @aiDotEngineer and i'll be at the Expo's poster area explaining the year's best survey paper on Agent Memory (Hu et al), as we did for @latentspacepod's Paper Club live from the floor with

Yohei Nakajima hosted a networking event in San Francisco bringing together the BabyAGI and Physical AI communities for casual conversation and relationship-building. The event likely focused on discu

LiteParse runs anywhere, including inside agent runtimes. To prove it, we built an email processing assistant using @flueai (the agentic framework by @astrodotbuild), @resend webhooks, and @tursodatab

LIVE at 12p PT/3p ET: AI’s cleanest stories are getting messy. Meta has excess compute. AI-heavy companies are hiring, not shrinking. And open models keep getting better. @DanielTNiles on what this me

LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of AI today. It's about being intentional in building and scalin