Search: “engineering”

With 4.7 you can push a lot further with one prompt. That means multi-file changes, ambiguous debugging, code review across a whole service. The stuff you used to break into small chunks because the m

Best part are retrieval and search details: >Agent queries differ from human queries & what good results means changes too >Parallel queries and ranking are both tools to the same outcome >Top-K preci

communication is hard! structured outputs make its more clear how subagents should communicate back to the main agent deepagents now supports structured output for subagents! an under appreciated piec

finally: @simonlast + @sarahmsachs on Latent Space! Notion has rebuilt Notion AI 5 times. This is the first time Simon has told the entire story. I've been trying to do this interview for ~3 years. We

Atom Computing, after eight years of operating in stealth mode, has announced its first open source project called Splitter, now available on GitHub. This marks a shift toward greater transparency and

There are multiple realities of AI right now. And what you have access to drastically changes your workflows, trust in AI, and ability to adapt to the future. Here’s the briefest state of the AI world

Two major shifts will be seen in Agentic AI after Harness and YOU MUST KNOW. 1. Workflow design of your agents matters a lot more than any frontier model selection. Till now we have mostly focused on

Elon on the origin of consciousness: 'Somewhere along that very long journey, consciousness arose. The molecules started talking to each other. Is everything conscious? Maybe. There's no discrete poin

just did our Monday morning weekly dev rel plan, feel free to steal :) shoutout to the great community that engages with us and gives us tons of feedback which makes doing this loop fun every week ❤️

The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so

Replit and Databricks have partnered to enable enterprise teams to build and deploy secure, production-grade data and AI applications by combining Replit's AI-powered development environment with D...

Finally some good news from @simonw: The Kākāpō parrots of New Zealand are having a fantastic breeding season. Media 'Using coding agents well is taking every inch of my 25 years of experience as a so

I was unable to retrieve the specific content of the linked tweet, as X (formerly Twitter) requires JavaScript and login to display individual posts. The search results did surface a highly relevan...

I strongly suspect that Claude Mythos is a looped language model, as described in the paper 'Scaling Latent Reasoning via Looped Language Models' from ByteDance The authors of that paper called out gr

Pills for llm coding from an OpenAI talk at @aiDotEngineer : - have single shared utils to do stuff like bounded concurrency - treat errors as values and part of the control flow - use telemetry for e

I think 'prompting' will keep being an incredibly high-leverage skill, like writing or public speaking. It is the skill of talking to agents, mediated by the harness. My main goal is to grow the bandw

🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals, and everything in between. Each episode

The specific tweet at the provided URL (status ID 2042211574056648726) is not publicly accessible or indexable by search, and the post-date status ID suggests it may be a future or fictional post b...

Anthropic's unreleased frontier model, Claude Mythos (internally codenamed 'Capybara'), was exposed through two separate leaks within the same week in late March/early April 2026. The Mythos model...

It seems like the day has come to leave Anthropic. Initially, I loved Claude Code. It was a good harness and a simple TUI... and I had learned to eat my tokens with a sauce of subsidy. Before joining

Perplexity AI has launched the 'Billion Dollar Build,' an eight-week competition inviting founders to use its agentic AI system, Perplexity Computer, to build a company with a path to a $1 billion...

Scaling code generation without scaling review risks turning coding gains into a larger “review” backlog (whether during PR review or later, when dealing with technical debt, incidents, or bugs). The

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

David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a

'a corollary is that information about product quality will become more important and impactful' This feels like the next evolution of SEO/AEO that every product will try to game. Even if agents do th

Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained

Awesome day, @satyanadella! Windows sparked a platform shift that created a new industry for NVIDIA. Then we invented programmable shading GPUs for DirectX, which led to CUDA. Then we partnered to bri

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

It is very cool to see llama.cpp on the big stage in todays Windows event! The software and hardware stacks are finally coming together. Our community has put a lot of hard work in the past years and

Useful paper on what an agent harness changes when the model stays the same. One takeaway: keep your harness prompt and tools small. In this study, that can cut costs by up to 3x without lowering accu

Context compression is a huge bottleneck for long-running agents. This work finds that context compression hurts long-horizon agents at a few specific points. They propose PAIR, which replays the agen

let me introduce you to the langchain stack 1. langgraph gives you this level of control 2. traces give you the complete run lineage 3. version your skills and instructions in context hub 4 & 5. deepa

Like Jev, I believe RL will unlock several more like this, slashing the cost of critical agent operations. flow-1 is competitive in performance, but a huge cost-saver for finding failures in agent tra

releasing my local AI slide deck covers from prefill vs decode, MoE vs dense, VRAM vs unified memory, quantization to speculative decoding, everything with llama.cpp feel free to reuse with attributio

Without a doubt evals are the biggest blocker in most agent development pipelines. We’re going to be changing that for everyone in LangSmith in a few short weeks… Hot take: evals are the #1 thing keep

I actually want personal operating systems optimized for co-working with AIs, including fine-grained ideas of security, easier ways to dynamically see & understand what AIs are doing, and independent

We're taking over a coffee shop on Union st. for 3 days of SF @Techweek_ by @a16z . The goal is to make it the busiest pop-up in the city this week. Mon to Wed, 9am to 4pm, franko & friends in the mar

Clef Flash (9 billion‑parameter) is a multimodal model hosted on Ollama that converts a given state and a schema of typed questions into actionable decisions. Its counterpart, Clef, is also available

Side note. The idea that current models are conscious is absurd and downright offensive. Do not confuse competent information processing and sentience, they are wholly unrelated. You can be entirely i

Open doors for open weights 🚀 @vLLM and Cohere are co-hosting a meetup in Toronto to discuss how we're contributing and pushing the future of open source. Plus, hear from a lead maintainer of vLLM on

a lot of robot video data for thee We’re making the egocentric internet searchable. VideoDB now lets you search 12M+ task episodes from every open datasets. Type “arms folding a towel” and get thousan

A thing to know about the AI business is labs that have frontier models can release half-built products and they work surprisingly well because the AI can just figure stuff out and improvise. Its like

Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon! It shows frontier performance in complex workflows, cyber defen

PDFs aren't built for machines: text shows up as glyphs with coordinates, tables as line segments instead of table structures. @jerryjliu0, CEO of LlamaIndex, digs into what that means for AI agents i

'Agent security will be solved in the open, collaboratively, together.' At Red Hat, open is the mission, so couldn't agree more. Red Hat has been part of the OpenShell project from the early days, as

could anything prove more decisively that Jensen Huang is a poor judge of character? his trust in OpenAI is entirely misplaced. 🚨BREAKING: “Months before OpenAI's artificial intelligence went rogue, t