A multiplayer agent harness for work. In Slack and on the web.

With this release MCP becomes a stateless protocol that scales on ordinary HTTP infrastructure. Every request now carries protocol version, client info, and client capabilities inside its _meta parameter, eliminating the need for a one-time initialization handshake. Clients that need to learn what a server supports can call the new server/discover method at any point.

Companies that invest heavily in AI grow headcount 10% over the two years following adoption. Entry-level headcount grows 12%.

Jensen Huang positioning: "Fireworks is the TSMC of AI Factories..."

In both cases, the country is celebrating a major birthday in the midst of a rising stock market and widespread fears of "technological unemployment" (mechanical power then vs. AI now); giddy wealth is coiled with economic anxiety; technology has transformed the way that people get information, mind-wiring us to a global cacophony of far-flung emotions (radio then vs. social media now).

From the homepage: "Build something Lovable. Create apps and websites by chatting with AI." Templates include spatial canvas tools, blogs, habit trackers, code-powered presentation builders, and e-commerce stores. Key metrics highlighted: millions of projects built, with substantial new projects created per week.

Transfer finding: "Learn it on the wrist. Use it anywhere on the body. Pretrain once on the wrist, then point the model anywhere. It holds up on body placements, and even sensor types like gyroscope and magnetometer, that it never saw during training."

Post-conditions pattern:

@ai_function(post_conditions=[check_length, check_style], max_attempts=5)
def summarize_meeting(transcripts: str) -> MeetingSummary:
    """Write a summary of the following meeting in less than 50 words."""

Post-conditions can be plain Python assertions or other AI Functions. The function only returns once eve

Custom agents provide a way to customize Kiro behavior by defining specific configurations for different use cases. Each custom agent is defined by a configuration file that specifies which tools the agent can access, what permissions it has, and what context it should include.

What the techno-determinism angle misses is: Why did these technologies catch on in the first place? Not every technology people have invented has caught on the way these forms have. They caught on in large part because of this impulse people have to live in a uni-context.

Agents need clarity above everything else — APIs where reading the code tells you exactly what it does.

Maintainers are now facing an assault on two fronts. The barrier to entry for generating code has dropped to zero... flooded repository gates with an alarming volume of low-quality, AI-generated pull requests. Maintainers who once spent their time writing code are now forced to become full-time, unpaid code reviewers.

Key positioning: "Stop relying on generic AI models. Databricks has the tools to build agent systems that deliver accurate, data-driven results."

In the run that used GPT-5.5 for both planners and workers, the workers alone cost $9,373. In the run where Opus 4.8 did the planning and Composer 2.5 did the work, the entire worker fleet cost $411.

A metastable failure is a self-sustaining congestive collapse in which a system degrades in response to a transient stressor (e.g., a load surge) but fails to recover after the stressor is removed. These rare but potentially catastrophic events are notoriously hard to diagnose and mitigate, sometimes causing prolonged outages affecting millions of

Model specs: - 975B total params, 41B active (Mixture-of-Experts) - Inkling-Small: 12B active params - 1M token context window - Pretrained on 45T tokens (text, images, audio, video) - Controllable thinking effort (0.2 to 0.99 sweep)

There are only two things you can say with certainty about token prices: we're in a supply crunch, and this is unstable. All of the variables are in play, and the market will get shaken out over the next few years to arrive at a new equilibrium.

We formalize this bottleneck as the intent-execution gap: the mismatch between what the model intends and what the harness executes, and vice versa. For example, in trying to revise code, a model may intend to edit a single instance of a function, while the harness accidentally modifies multiple instances.

Note: LinkedIn blocked direct crawling of this article. The following is reconstructed from the article title, author context, and surrounding discourse on the same topic.

Sponsorship: Diamond level, Booth B207, Seoul South Korea

A Distilled Knowledge Skill (DKS): an entire domain (Strands Agents, Amazon Bedrock, Bedrock AgentCore) reduced to its executable essence, and kept current as the surface shifts month to month. The research is already done; you skip straight to building.

Over the past few months, four AI giants quietly rebuilt the same thing at once: AWS, Microsoft, Google, and Anthropic each shipped agent runtime updates that point to the same architectural shift. [...] It is a move from request-level load balancing to session-aware execution.