Looking forward to speaking at @aiDotEngineer New York, Oct 12–14. Come say hi — ai.engineer/nyc/2026

can confirm. ran @latentspacepod AINews side by side with 6 Sol and the difference was night and day: latent.space/p/ainews-claude… 5.5 Opus is the new default model for AINews going forward. so much more concise and tasteful reporting, with much less slopese than even 5 Opus.

Coining “EvoUndo Engineering”: building agents that can safely undo their changes.

What happens when an autonomous agent does something BAD? We’re coining the term “EvoUndo Engineering” for making agent actions recoverable and reversible. Paper: arxiv.org/abs/2608.28363

part of this is in how ~everyone with a platform here speaks about LLMs for the past few months i rely on LLMs as excitedly as anyone, but... are we using the same models, guys?! the frontier is still dumb as a brick 20%+ of the time and needs more hand-holding than a freshman it's just that for some VERY specific types of work, like all the beautiful discovery announcements in the recent past, this hand-holding was painstakingly and expensively done by the labs for us (fantastic btw) but... 99% of the time, i am not searching under the lamppost of the AI lab's over-optimized workflows, so that high cost of alignment to the task is mine to handle and i absolutely do it because it's extremely valuable, and if it needs to be said, i think the progress has been far beyond what i'd have guessed and it's only gonna get far better from here. but don't let the jagged frontier of capabilities delude you into thinking that things are plainly "superhuman" at any *coherently broad* set of capabilities, because A LOT remains to be done (and i think it will be)

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

The ACM CAIS 2026 session recordings are now live. Great to see the talks from San Jose available online, including our presentation on The Verifier Tax. Check out the full playlist below.

If you missed the ACM CAIS 2026 conference and want to know which paper won the Best Paper Award, check out the YouTube video piped.video/watch?v=-vnH1WkQ… of their presentation. Great work! Shuren Xia Jorge Ortiz and the entire team!

Anthropic pays $750,000+ a year for engineers who can build LLM architectures from scratch. Stanford taught the entire thing in 1 hour lecture & released it for free. Bookmark & watch this today before someone takes it down and read this article "How claude uses context"

Sometimes, a GIF speaks louder than words: consistency compounds. What do you think?

Tomorrow I’ll show how to unify your data, services, and systems into a single virtual filesystem for AI agents using Mirage github.com/strukto-ai/mirage Instead of building custom integrations for every tool, expose everything through a familiar filesystem interface. Join if you’re curious about the future of agent system. #AIAgents #AgentSystem #VirtualFilesystem #Mirage

Thanks for discussing meta-harness @lilianweng ! A very clearly written summary of the state of harness engineering + RSI. I often get the question"what can a harness actually improve?" which i only had partial answers to; this post lays out the whole picture in one place

The Verifier Tax: Horizon Dependent Safety--Success Tradeoffs in Tool Using LLM Agents | Proceedings of the ACM Conference on AI and Agentic Systems dl.acm.org/doi/full/10.1145/…

TIL verifier tax: an AI agent can complete a task and still fail. It might get the right outcome while breaking a policy, skipping an approval step, or exposing sensitive data. The task is done, but the process wasn't safe. Counts as success or failure? dl.acm.org/doi/full/10.1145/…

Ty @heathercmiller for organizing the amazing @CAISconf event and @trq212 for the amazing talk! Had hella fun this week 🎉🎉🎉

Really happy to share that our paper -“Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain” has won Best Paper (Outstanding Problem Paper) at @CAISconf 🏆 TL;DR - Poison ~2% of an AI agent’s fine-tuning traces and you can plant a trigger-activated backdoor that leaks confidential data >80% of the time. Guardrails completely miss it. (and thanks GPT for editing me into the team photo so cleanly nobody can tell I wasn’t actually there 😅)

@CAISconf was sold out but small, focused on a particular well-scoped area (compound agentic systems). Some workshop papers were submitted as late as just a couple weeks before (fresh content), and good thing, too! Agentic systems already look quite different today than even 3 months ago. Perhaps the systems focus naturally attracts researchers who are inclined to build prototypes and libraries (not just publish), but I was still pleasantly surprised to see how many members of the Laude community had independently identified this conference as one they wanted to submit to and attend. On top of that, throwing a lounge after hours with food, drinks, demos, salon-style conversation, (and a mini podcast studio, because why not?) made it easy to get an even higher concentration of interesting people with interesting half-baked ideas in a particular niche that happens to be on fire right now. Loved the experience. Well-done, CAIS organizers (@heathercmiller, @lateinteraction, @matei_zaharia, @deeptir18, et al). Same time, same place next year?

One problem, two solutions, one through-line: agentic systems need real guarantees, not heuristics. All three, plus 60 more papers: caisconf.org/program/2026/pa…

Excited to share that our paper, The Verifier Tax: Safety–Success Tradeoffs in LLM Agents, will appear at @CAISconf 2026 in San Jose, where we'll also present the work. alphaxiv.org/abs/2603.19328 Thanks to the reviewers, @lateinteraction, @heathercmiller, and @aviaviavi__ 🙏

Most ML models do not fail in training. They fail in validation. As ML systems scale, validation is becoming the real bottleneck. Speaking this Friday, April 24, at the NC State MFM Workshop on Quantitative Finance on how TanML approaches this. #MachineLearning #MLOps #AI