I wonder if Continual Learning will be solved this year. It seems to be an important stepping stone for AGI. From what I hear, Ilya Sutskever’s company SSI might be working on it. That could be super interesting if their first public release makes some progress on it.

Loved this 22-minute talk on continual learning for AI agents. Must watch for anyone looking to get agents performant and into production. Credit: @FeiziSoheil at @aiDotEngineer • Agent learning can happen at three layers: the model (weights), the harness (prompts, tools, skills, code, workflows), and memory (session or persistent). • Two fundamental challenges: (1) getting feedback, meaning how do we know if the agent did well and what it should have done instead, and (2) acting on that feedback, meaning deciding which layer or component to change and how. • Feedback sources differ by stage: In development you have benchmarks with evaluators that score pass/fail. In production you only have logs, which can be judged either automatically (LLMs or code analyzing the log, which is scalable) or by human experts (low volume but critical domain knowledge). • Logs plus feedback aren't enough because they're not testable: A single log with feedback is one observation of what happened. You need to lift it into a replayable learning environment, a simulation with tools, users, and defined evaluators, so candidate fixes can be run, verified, and compared. • Three ways to optimize the agent, with tradeoffs: Model-layer updates (SFT, RL post-training like DPO/GRPO, LoRA) are expensive and need benchmarks and evaluators. Harness updates (trace-to-harness coding agents, prompt search like GEPA) are flexible but either untestable and "vibe-based" or benchmark-dependent. Memory updates (fact storage like Letta/Mem0, skill distillation) are cheapest and fastest but usually unverified. • A good learning engine makes "the smallest durable change at the right layer" of the agent. • Verifiable continual learning (VCL): Improve an agent from its own experience where every fix is proven to help and proven to break nothing that already worked. It requires an executable test (replayable failure), a measured delta (score before and after), and regression tests (prior tests still pass). • Four principles of practical VCL: Replayability (turn one-off failures into rerunnable tests), holisticness (one failure can have causes in memory, prompts, tools, workflow, or model, so route the fix to the right layer), lifelongness (fix new failures subject to no regression on past environments, with regression handled inside the optimization loop rather than post-hoc), and efficiency (the loop must run frequently and cheaply, without scaling linearly as past environments accumulate). • Three takeaways: (1) Agent continual learning isn't necessarily fine-tuning; many useful updates live in the harness and memory layers. (2) Production logs are not learning environments and must be transformed into replayable ones. (3) The frontier is regression-aware improvement: fixing new failures while verifying you don't break old ones.

Can you imagine the regulatory mess once AI cracks Continual Learning? Right now, model weights are mostly fixed after training; you can fine-tune, patch, and steer the system afterward, but the core model is still treated as a relatively stable artifact. With Continual Learning, that assumption breaks, as models may keep modifying their weights, absorbing new information, and developing new capabilities after deployment. So how do you "test" such a model for capabilities? You don’t certify a thing anymore, you chase a moving target, and that quickly turns into a never-ending cat-and-mouse game between regulators and models that keep changing. Continual Learning is definitely coming, and it's not too far away.

This represents a vital step towards closing the gap between training and inference, and moving towards continual learning in production. Several of our customers have been training with BYOH. Read the full report.

I'll be at ICML July 7th-10th, hit me up if you want to chat about continual learning, AI policy, etc! I’m giving an invited talk on evaluating continual learning at the CATS workshop on July 10th at 8AM KST and @aczhu1326 and I are presenting a poster on Advisor Models on July 8th at 10:30AM KST (Hall A #2107#).

We’re partnering with the developers of @EveOnline to explore the next frontier of AI research in games. EVE's complex, player-driven universe is the perfect safe sandbox to test agents on memory, continual learning, and long-term planning. Find out more →

GLM 5.1 is coming Coding is the cornersone and Long Horizon Task (LHT) is the new feature this time. focus more on 1. memory 2. evolving/continual learning 3. self judge/reflextion.

Recent thoughts: The Shift to Long-Horizon Tasks The most likely breakthrough this year will be in long-horizon tasks. We are moving toward a stage where Large Language Models (LLMs) learn to complete extended, complex missions by interacting with Agent environments. This is perhaps where the true value of LLMs lies. Take cybersecurity as an example: imagine a model that continuously hunts for software bugs and vulnerabilities. While it sounds like a search process, it’s actually the model learning the high-level intuition and methodology of a professional hacker. Unlike humans, AI can run 24/7 without fatigue. It could potentially find exploits at a much higher frequwill ency and claim bounties on platforms like HackerOne or BugCrowd. It sounds fun, but fundamentally, it's a revolution that displaces the hacker. If even hackers are being "disrupted," one can only imagine the impact on general programmers. From One-Person to None-Person Companies Building on long-horizon capabilities, Autonomous Agent Systems (AAS) will inevitably become the next frontier. Last year, we were discussing the rise of the "One Person Company" (OPC). I didn't expect us to move so quickly toward the "None Person Company" (NPC). It’s an ironic twist—we might all end up as NPCs in this new ecosystem. Engineering the Impossible: Memory and Learning To realize the vision above, we must solve three technical pillars: Memory, Continual Learning, and Self-Judging. I used to think these would require massive paradigm shifts and years of research. However, the pressure from both the technical and application sides is so intense that we are seeing these capabilities emerge through ingenious engineering "tricks": Memory: Long context windows (1M+) and RAG have significantly bridged the gap. Continual Learning: While true continual learning remains difficult, the release cycles are shrinking. Global models are updated monthly; domestic models are catching up. If we reach weekly updates by next year, it will effectively function as continual learning. Self-Judging: This remains the most elusive, yet models like Opus 4.7 are already demonstrating early self-correction and judgment capabilities. The Self-Evolving Endgame The most difficult—and most promising—path is Self-Evolution. The current wave is incredibly fierce. I suspect that models like Claude may have already achieved a baseline for self-training: writing their own code, cleaning their own data, generating synthetic data, and then training on it. It might "waste" some compute, but it saves the most precious resources: human labor and time. In the LLM era, speed is everything. Rapid iteration is what creates the cognitive gap between leaders and followers. Claude’s rumored 2-million-chip cluster for next year is likely dedicated to exactly this: autonomous model self-training. Technical Summary: 1M Context: Necessary baseline. Memory & Continual Learning: Prerequisites, likely solved first via "tricky" engineering. Harnessing Environments: The breakthrough point. Self-Judging: The tipping point. Full Self-Training: The endgame. Redefining AGI and the Industry If this is the road to AGI, then AGI’s definition should be the sum of all human collective intelligence, not just an individual’s intelligence. It must possess the creative capacity to produce something as profound as the "Theory of Relativity"—meeting the bar set by Hassabis. During this transition, every APP will need to be reconstructed as AI-native. In fact, we might move past the concept of APPs entirely. The most significant challenge will be the reconstruction of the operating system itself. In the future, you won’t see a traditional desktop; you will see an LLM OS, where applications are "generated on demand." This challenges the 80-year-old Von Neumann architecture and represents a total upheaval of the computer science industry. The Irreversible Wave From completing long-horizon tasks to fully autonomous operations, every sector—Security, Finance, Law, E-commerce—will be reshaped. Many friends have reached out lately, asking how to transform their enterprises to keep pace with AI. But few truly realize that this irreversible process has already begun. As this massive technical wave hits, we must be prepared to act, but we must also start thinking seriously about how to regulate it.