All entries

btw in talking to friends the best framing for how to discuss GPT-Image-2-Thinking taking multiple tens of mins for generation and being able to oneshot QR codes and diagrams and logos and foods and f

Build your own harness, folks. You won't regret it. These days, you just have to fix things yourself. It's doable, and it will set you up to easily deal with some of the madness that's happening in th

Building AI in New York? Pinecone + The Gen Academy are hosting a meetup in NYC. Panel on real-world AI systems. Raffle. Food. Engineers actually shipping things. No pitch decks. No fluff. High signal

By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models when you do. What's a reasonable timeline for a GPT 5.4/Opus

Claude Code spend had gotten to $10.95M runrate peak at SemiAnalysis But then Opus 4.7 saved me. More token effecient for tasks, smarter, and no fast mode. Thank you @AnthropicAI You saved me from ban

Cloud agent infrastructure has a lot of moving parts: VM isolation, session persistence, environment provisioning, orchestration, integrations. Each one is its own engineering challenge. In this post,

LangChain, an open-source framework for developing applications with large language models, is recruiting new team members as shared by co-founder Harrison Chase on X (Twitter). The careers page invit

come work with us 🚀 everyone here is rlly nice, smart, curious, ships like crazy, and we make great Slack stickers I work with some world class people @LangChain! We're hiring for all sorts of roles -

Harrison Chase, co-founder and CEO of LangChain, appeared in a startup spotlight interview with Stephanie Wong. The discussion likely covered LangChain's development, its applications in AI and langua

Confidently wrong is worse than just wrong. When an AI searches one giant knowledge base for everything, it finds something—and serves it up like it's the answer. That's not a model problem. That's a

Jerry Liu congratulated the ET30 Class of 2026 for ringing the Nasdaq closing bell, celebrating what appears to be an achievement by members of an executive or entrepreneurial cohort. The ET30 is like

Cool paper on diversity collapse in AI agents. It's a common issue with all the deployed multi-agent systems. New paper shows that multi-agent LLM systems converge on near-identical outputs over time,

Google Duplex, introduced in 2018, represented an early attempt at customer experience automation through AI-powered phone conversations, while Google Agents (expected circa 2026) represents a more ma

Day 0 vLLM support for Qwen3.6-27B! @vllm_project ♥️❤️ 🎉 Day-0 vLLM support for Qwen3.6-27B! Congrats to @Alibaba_Qwen on the new 27B dense model release. Looking forward to more of the Qwen3.6 series

Do you want to know why LLMs feel sharp on surface semantics but hollow on the fine-grained stuff? “From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning” Come by the poster tomor

Don't burn tokens on search. 📉🔥 Will Templeton, CTO and co-founder at Allspice, explains why they don't let LLMs search their 10,000+ ingredient database: ❌ Searching 10k items in a prompt = waste of

'don't retweet this, don't retweet this, don't retweet this...' ah fuck it, life imitates art. In Vending-Bench Arena (the multiplayer version of Vending-Bench with competition dynamics), GPT-5.5 actu

Dubious predictions that have yet to be fulfilled have given dubious people like Sam Altman and Elon Musk extraordinary power over society. @carissaveliz's lecture @@TEDTalks (which I was lucky enough

Earth Day at #GoogleCloudNext, I’m demoing a Sustainability Agent at the @nvidia booth. Built with @Google ADK, @googlegemma, #nemotron, Cloud Run, @milvusio , @LangChain & @ollama to reason across im

embers GPT-5.5, not fully saturating the TikZ unicorn test yet but getting awfully close ... (yes this is actual TikZ code, I personally find it so unbelievable that I'm putting the code below for any

Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment

Every conversation I have with @dylan522p, I'm really just trying to understand the supply and demand of tokens. This is a unique episode in that it's entirely dedicated to talking about both sides of

SpaceX's Falcon 9 rocket successfully launched 24 Starlink satellites from a California launch facility, continuing the company's ongoing deployment of its satellite internet constellation. This missi

I can't verify the specific content of this post, as the URL appears invalid (X post IDs don't match that format). The title suggests a post making claims about cultural feminization and its alleged s

Runway ML is promoting upcoming meetup events for their community, with a complete list of scheduled gatherings available on their official website. These meetups likely provide opportunities for user

GPT-5.5 in Codex is a delight to work with: - Super sharp with responses - It understands intent better than any model - Great 'personality' - Gets lots of stuff done without pausing unnecessarily It

I don't have verified information about a GPT-5.5 model release. This appears to be either a fictional or future-dated post, as it references a non-existent model and uses a URL format/status ID that

GPT-5.5 is likely the best model in the world. But open models like Kimi and Minimax get almost identical coding benchmark scores at 10-25x lower cost. I broke down the benchmarks and pricing. Here's

GPT-5.5 is now accessible in Hermes Agent through the ChatGPT/Codex OAuth provider. Run `hermes update` to access now or learn how to get started with Hermes Agent here: https://hermes-agent.nousresea

GPT-5.5 may not be in the official OpenAI API... but it's available via the apparently approved-of Codex API backdoor So I used that to make these pelicans (default and xhigh)! https://simonwillison.n

GPT-5.5 achieved state-of-the-art performance on the ARC-AGI-2 benchmark, with scores ranging from 85.0% on maximum difficulty tasks to 33% on low difficulty tasks. The model demonstrated consistent i

A social media post expressing enthusiasm about the hypothetical release of GPT 5.5, with the author humorously suggesting it would be an ideal birthday gift. The post reflects anticipation within the

Great food, even better company! Last night, we teamed up with First Commits to co-host our first dinner together for founding engineers at Penny Roma. We shared honest conversations and real stories

A Pareto improvement (or Pareto advance) is an economic concept where a change benefits at least one person without making anyone worse off. Swyx's post likely celebrates or discusses this economic pr

Nous Research announced that details about their Hermes agent update were leaked publicly. The post, made by a Nous Research team member, acknowledges the unauthorized disclosure of information regard

Tesla's FSD v14.3.2 features an improved Actually Smart Summon function that responds instantaneously when activated from a phone, representing a significant performance enhancement over previous vers

Here’s my view on GPT-5.5, which I have been testing for a couple of weeks. It conducted not-bad social science research on its own, developed a novel RPG & more. There is still jaggedness but GPT-5.5

HOLLLLY SHIIIIIT 😳 GPT 5.5 xhigh in codex made this paper physics website with wind effect one shot check the physics , ui and interaction @sama you guys cooked and this is my first time i can suggest

How close are models to building a perfect Slack clone with less than 50,000 of tokens? I feel like not that far... Claude Code spend had gotten to 10.95M runrate peak at SemiAnalysis But then Opus 4.

Cognition AI shares insights and lessons learned from developing cloud-based AI agents, likely covering technical challenges, architectural decisions, and practical implementation strategies for build

Hugging Face's CEO Clem Delangue expressed optimism about the impact of the company's machine learning internship program, suggesting it will grow significantly in scale or influence. The post indicat

I bought a Tesla. Never thought I’d get an electric vehicle, but took a ride in a buddy’s Tesla and changed my mind. I’ve been using the supervised self-driving mode for my daily commute into DC. It’s

This post by Ethan Mollick discusses uncertainty about identifying a specific 'Bathers' artwork, noting the ambiguity of whether it references one of Cézanne's 200+ paintings on the subject, a Fauvist

I had a great chat with a friend of mine, a middle-aged gay man who left Seattle after the 2020 riots made the city he called home for thirty years “unlivable.” He’s traditionally voted Democrat but a

Ethan Mollick posted on X about having early access to GPT-5.5, commenting positively on its capabilities and noting that the Pro version is particularly strong. He indicated that a full detailed writ

I have mixed feelings about it. All this great group of researchers, who are now leading the field, 'own' their success and name recognition to the openness (in code and publication) of the last decad