AI

It’s Monday, and so it’s time for the next issue of Chronicles. Last week was very significant because it represented a tectonic shift from using expensive, efficient models to cheap and still very efficient models. In other words, AI is getting democratized.

Let’s start with the hardware. This week we’ve seen interesting news from OpenAI, which published the first benchmarks for their Jalapeño chip, a custom inference chip designed with Broadcom. It’s pretty impressive. They published over 700 tokens per second per user on DeepSeek R1 at concurrency of one, and about 1400 on Kimi K2.5 and GPT-OSS. The variety here matters because the chip has been benchmarked not only on OpenAI’s own models but on open-weight models from other vendors as well. The chip is critical in the ongoing price war with the Chinese providers. Remember that last week we had data on cutting prices on their Sol model by 20% on input and 33% on output, which is a promotional window that expires on 21 November, and a week before that they cut the price of Luna by a whopping 80%.

Last week was all about the harness. Gone are the times when the models were all things-in-themselves. Now, as with early Homo erectus, the tools are the factor of survival. If we look at the types of harness-related posts and announcements, we will see three trends.

Harness products

Several companies have released either agents or infra for agents at once.

OpenAI has released the execution framework that their Codex (the CLI one) is based on. Unsurprisingly called Harness, it is their answer to the Claude Agent SDK and the GitHub Copilot SDK. The Harness provides the execution loop, memory, tools, and other necessities of agentic life. You can use it in three different ways. First, you can just use codex exec to run non-interactive jobs. Second, you can use the Codex SDK for building workflows. And last, you can use app-server to build apps that require conversation handling. One point worthy of attention is that they claim that the Harness improved the performance of the GPT-5.6 Sol model from 13.3% to 38.3% on ARC-AGI-3. It’s unclear what harness (not capitalized) was used as a baseline, though.

Over the last week, we’ve seen some announcements from both the highest-end and lowest-end sides of open-weight models. At the same time, labs are starting to think that maaaybe, just maybe, we move too fast and we need to stop and think. So, in their free time, they are starting price wars.

Models, hi

Last week we saw a bunch of releases of very large open-weight models. Z.ai shipped GLM-5.3, which is relatively small, just 743B, DeepSeek published their 1.6T V4-Pro weights under the MIT license, and Alibaba surprised with a whopping 2.4-trillion-parameter Qwen3.8. Although they are open, doing anything meaningful with models of this size requires hardware not a lot of individuals have, which defeats their openness a little. On the other hand, they open possibilities for 3rd-party hosting and incentivize the price wars I will talk about below.

This article opens a series (I expect it to become one) of posts in which I review the AI-related events of the past week and try to figure out how they fit into the bigger picture.

The main highlights of the past week are:

1. We continue to see real-world security breaches caused by AI system evaluations, and it looks like another race.

2. Major regulations came into force.

3. Data centres face increasing opposition from local communities. Companies seek workarounds.

How Long Contexts Fail

How to Fix Your Context

Long context is your friend… when we are talking about summarization and retrieval. For agentic workflow it is often detrimental due to reasons such as:

1. Context poisoning, where the model hallucinates and messes with its own context. The ripples are powerful and they die slowly;

2. Context distraction, where the model starts to repeat itself instead of trying new strategies;

3. Context confusion, which happens when one gives the model too many tools (sometimes 2 is too many);

I usually approach shiny new things with a healthy dose of skepticism. Until recently, this was precisely my attitude toward multi-agent systems. This is hardly surprising, given the immense hype surrounding them and the conspicuous absence of genuinely successful examples. Most implementations that actually worked fell into one of the following categories:

1. Agentic systems following a predefined plan. These are essentially LLMs with tools, trained to automate a very specific process. This approach allows each step to be tested individually and its results verified. Such systems are typically described as a directed acyclic graph (DAG), sometimes dynamic, and developed using now-standard primitives from frameworks like LangChain and Griptape. The early implementation of Gemini Deep Research operated this way: first, a search plan was created, then the search was executed, and finally, the results were compiled.
2. Solutions operating in systems with a feedback loop. Various Claude Code, Cursor, and other code-generating agents fall into this group. The stronger the feedback loop—that is, the better the tooling and the stricter the type checking—the greater the chance they won’t completely wreck your codebase.
3. Models trained using Reinforcement Learning, such as those with interleaved thinking, like OpenAI’s o3. This is a separate, very interesting conversation, but even these models have a certain modus operandi defined by the specifics of their training.

Meanwhile, open-ended multi-agent systems have largely remained in the proof-of-concept stage due to their general unreliability. The community lacked a clear understanding of where and how to implement them. This was the case until Anthropic published a deeply technical article on how they developed their Deep Research system. It defined a reasonably clear framework for building such systems, and that is what we will examine today.

The public conversation about AI and labor is stuck in a tedious loop. “AI will take our jobs,” declare the headlines, a statement of faith in technological determinism that serves as a conversation-stopper, not a starter. A more useful, if still imperfect, entry point begins with a simple economic model.

It starts with an observation, such as Arvind Narayanan’s on radiology: AI has surpassed human performance on many discrete tasks, yet the number of human radiologists continues to grow. This suggests the dominant effect isn’t automation, but augmentation. My initial take was that this boils down to a classic supply and demand problem. One AI-augmented specialist can do the work of many, increasing supply. In fields with vast, unsaturated demand—think of the queues at hospitals or the perpetual backlogs in software development—this new capacity will simply be absorbed. Problem solved.

The Model Context Protocol, despite its aggressive adoption (or perhaps because of it), continues to evolve. Anthropic recently updated the MCP specification, and below, we’ll look at the main changes.

Security Enhancements

An MCP server is now always classified as an OAuth Resource Server, and clients are required to implement Resource Indicators (RFC 8707). This is necessary to protect against attacks like the Confused Deputy. Previously, tokens requested by a client from an authorization server were “impersonal,” meaning they could be used by anyone. This allowed an attacker to create a phishing MCP server, deceive a client, steal the token, and use that token to gain access to the real MCP server.

At a time when the words “AI” and “hype” have become almost synonymous, it’s crucial to be smart about choosing your sources of information. There is far too much information noise out there, and sifting through the sea of articles from various AI evangelists and generated garbage to find something truly worthwhile is incredibly difficult.

In this post, I’ll share the materials I read to stay up-to-date on the latest developments.

It’s summer. Time to plan a vacation getaway. You open ChatGPT, select the increasingly popular “Travel Advisor” GPT, and start discussing options. The advisor gives excellent suggestions, offers fascinating details about local attractions, generates pretty good itineraries, and generally leaves a great impression. Sure, some oddities pop up here and there, but you dismiss them as harmless hallucinations. You settle on Barcelona. Excellent choice. In the same chat, you switch to another familiar and popular GPT, “Booking Agent,” which has never let you down, and book your accommodations.