Search: “claude”

Great new paper from AWS on agent handoff tax. If you build agents today, you need to understand the so-called handoff tax. (bookmark it) Escalating to a stronger model mid-run is usually the resort w

Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the

Hosting the 2nd founder dinner in sf on August 31 with @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Agents are increasingly capable of solving tasks for longer task horizons without

On August 26, 2026 Z.ai reported that its Code‑Bench metric—which assesses real‑world coding performance—shows GLM‑5.3‑Flash outperforming GLM‑5.2 at every effort level. The new model’s results are on

i’m seeing SO many US companies shift away from frontier models to open source in the last 4 weeks. cost and privacy are big factors but more so people are realising fine-tuning and training their own

Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Talking about existing moats in the AI era. Frontier labs are moving past mode

Heard a crazy stat the other day. Video generation represents around 70% of the share of AI token consumption in China. A combination of short form content and robotics. In China, video models are gro

One of the interesting properties we’ve observed around schema-guided, complex document extraction tasks 📑 is that coding agent harnesses are good baselines (in terms of cost/accuracy) for longer docu

Banger paper from Google DeepMind. It's on the very hot topic of model routing. Routers assume the value estimate is free. Working out which specialist handles a query best costs money too, and it is

🐦Ornith 1.5 series models are now available on ollama! 🫡Thanks to our awesome friends at @ollama 👀Come give Ornith 1.5 a try! https://ollama.com/library/ornith-1.5 Aloha! 🌺Introducing Ornith-1.5, a fa

So @swyx and team are still judging his amazing “Kill My SaaS in one weekend” contest, where you could win 10K to replace his 40K/year conference submission (CFP) and scheduling SaaS. I think 68 peopl

Aloha! 🌺Introducing Ornith-1.5, a family of open-source LLMs spanning 9B Dense, 35B MoE, and 397B MoE, trained with self-improving strategies. It achieves state-of-the-art performance among open-sourc

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the mo

Pareto frontier is live in Agent Arena! Dive into model performance on real-world agentic tasks, compared to the median cost per task. The current models on the Pareto frontier for Agent Arena are: -

Remember my discussion with @dwarkesh_sp about revenue forecasts for Anthropic? He is basically projecting continuous exponential growth for Anthropic’s revenue run rate; I have been saying it will fl

GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za

1/2 the turns and 25% of the tokens. Task/Token is something to watch. Is Grok 4.6 inside Grok Bot? Has this been revealed yet? Have I missed it? I’ve been wondering what magic allows grok bot to just

We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for

If you hand-tune agent harnesses, this one is worth your time. AutoDesign puts the harness itself inside the optimization loop. A meta-harness optimizer reads rollout feedback and directs a code agent

My Al Agent Workshop with @mcuban might be the best workshop we've ever had. Over 20,000 people registered and my inbox is filled with people making REAL CHANGE in the way they work and what they're a

This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine

Within Devin, Gemini 3.7 Flash performs particularly well on tightly scoped refactors, where it delivers minimal diffs that match repo conventions. Gemini 3.7 Flash is available at a 50% discount for

18 two-word AI prompts I'm kind of obsessed with: 1) now what - great for when you've wrapped up a project or big push and you still have energy and want AI to give you more 2) plz fix - usually accom

Everyone else is talking about building ASI to like monopolize b2b saas and Elon is talking about building a kardashev II sentient sun Media It’s always funny how people in SF twitter bubble will say

Grok 4.6 is an excellent model. I’ve been using it heavily for the past couple of weeks and it handles everything from simple coding & code review all the way to designing and debugging complex system

Interesting research suggests caution in determining which AI company is winning by looking at any one source.. OpenRouter seems to show open weights winning over time, but work submitted to Pangram i

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B

With the smartest person I know, @HarshSensei, we're building evsys-sdk for the community, this open-source repository allows anyone to build their own continual learning system with first-class suppo

we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap! We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Pri

Grok Imagine is focused on professional usefulness, fun for consumers and overall ease-of-use Grok 4.5 just ranked #1 on Design Arena for Daily Usage - measuring the average unique users actually inte

Grok Build is quickly turning into an all-in-one creation environment It can now also generate images and videos with Grok Imagine directly inside your workflow You can create custom visuals for websi

The future of FDE work seems closely related with all work around evals/posttraining/RL envs. FDEs are effectively responsible for the following: 1. Define the business problem. 2. Codify the business

Codex is overoptimised for large models: it ranks 2nd out of 10 for GLM 5.2 but drops to 9th place for Gemma-4! Almost all the effort in this field goes into tuning the weights. We wanted to know how

turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto m

The tweet is a question from user Simon Willison (posted on 6 Aug 2026) asking which OpenAI API model corresponds to the ChatGPT “GPT‑5.6 Instant” version. No answer or clarification is included in th

One of the things the pelican benchmark is still useful for is visually representing (to a tiny extent) the improvements in a single model family Here's Meta AI's Spark (8th April), Spark 1.1 (9th Jul

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to

SITUATION DETECTED: Prime Intellect is releasing Prime Agent, a self-improving harness for coding and long-running autonomous tasks. The team reports 95.5% on ARC-AGI-3, above the human baseline, and

Nate is right (full context can lead to a degradation of chats in several different ways) but you can't ask the AI about stuff like this as they have bad self-knowledge A good approach is to compact t

Another day and another full frontier model running on your computer. Been teething DeepSeek V4 Flash on over 60 employees at The Zero Human Company for a few hours and it is stunning. Between Kimi K3

Cybersecurity isn’t a fortress problem, it’s an immunity problem. Think vaccines. Eliminating pathogen is not practically possible. Vaccines don’t eliminate pathogens. They teach the immune system to

3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly

Fascinating: OpenAI’s @deanwball is saying Astra can do anything, and it’s not even clear it can do “anything” in math (let alone anything in more or open-ended, less formalizable domains). I dropped

This is both a real incident (in that the AI really did get unauthorized access to real systems) and also something it was (sort of) prompted to do. In a review of our cybersecurity evaluations, we fo

“AI Meltdown” is the scenario where the agent goes off the rails and forgets/ignores all previous instructions and soft guardrails. No prompt injection or malicious actor is needed for this to happen.

BREAKING: Grok 4.5 (high) ranks #1 on the HighWalk benchmark, which tests how well AI agents update technical specifications from code changes. Grok delivered the best combination of quality and opera