The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Agent Framework’s CodeAct and Hosted Agents Are Microsoft’s Answer to the Two Things That Kill Agent Demos: Tool Latency and Production State
azure-ai

Agent Framework’s CodeAct and Hosted Agents Are Microsoft’s Answer to the Two Things That Kill Agent Demos: Tool Latency and Production State

Most agent demos die the same way: not because the model cannot reason, but because the system spends too many turns asking itself which tool to call next, then collapses when someone asks where the state lives in production. Microsoft’s latest Agent Framework announcement is useful because it goes
05 Jun 2026 6 min read
Pydantic AI 1.106 Fixes the Kind of Streaming Bug That Breaks Real Agents Quietly
ai-frameworks

Pydantic AI 1.106 Fixes the Kind of Streaming Bug That Breaks Real Agents Quietly

Pydantic AI v1.106.0 is the kind of release that will not trend on Hacker News and will absolutely save someone’s production agent from lying quietly. The release is small: xAI provider ergonomics, a data URI parser fix, and one streaming bug fix. But the streaming fix is
05 Jun 2026 5 min read
Google ADK 2.2 Makes the Default Model a Migration Decision, Not a Footnote
ai-frameworks

Google ADK 2.2 Makes the Default Model a Migration Decision, Not a Footnote

Google ADK 2.2.0 looks like a normal framework release until you hit the default model change. Then it stops being a changelog and becomes an operations memo. The Python release moves LlmAgent.DEFAULT_MODEL from gemini-2.5-flash to gemini-3-flash-preview. Google has a rational reason: Gemini 2.5 Flash
05 Jun 2026 5 min read
Microsoft’s Agentic AI Taxonomy Update Says the Security Boundary Is Now the Agent Session
agentic-coding

Microsoft’s Agentic AI Taxonomy Update Says the Security Boundary Is Now the Agent Session

Agentic AI security has spent the last year stuck in an awkward phase: everyone agrees prompt injection is real, but too many defenses still look like chat-app bandages wrapped around systems that now browse, write code, invoke tools, remember state, delegate work, and ask humans to approve things they barely
05 Jun 2026 5 min read
Utah’s Gemini Deal Turns AI Governance Into School-District Ops
google-ai

Utah’s Gemini Deal Turns AI Governance Into School-District Ops

Utah’s statewide Gemini for Education deal is easy to flatten into the least useful headline: students get AI tools. That is not the interesting part. The interesting part is that Gemini is being packaged as managed public-sector infrastructure, complete with privacy promises, admin controls, training, curriculum, credentialing, and a
05 Jun 2026 4 min read
Google’s Meitner Energy Center Is the AI Roadmap With a Power Bill
google-ai

Google’s Meitner Energy Center Is the AI Roadmap With a Power Bill

Google’s Meitner Energy Center announcement is technically a data center story. Read it that way and you will miss the point. This is an AI roadmap story with the power bill included. Google and Intersect are building the Meitner Energy Center in Gray and Roberts Counties, Texas: a new
05 Jun 2026 4 min read
Kaggle Benchmarks Makes AI Evals Feel Like Code Review
google-ai

Kaggle Benchmarks Makes AI Evals Feel Like Code Review

Kaggle Benchmarks getting a local development workflow sounds like a small tooling update. It is not. It is Google taking one of the least disciplined parts of AI engineering — “we tried a few prompts and it felt better” — and pulling it closer to the place where software teams already know
05 Jun 2026 4 min read
Code2LoRA Tries to Make Repository Knowledge a Weight Update, Not Another Giant Prompt
ai-models

Code2LoRA Tries to Make Repository Knowledge a Weight Update, Not Another Giant Prompt

Coding agents have been brute-forcing repository knowledge with bigger prompts, better retrieval, and a lot of hope. Code2LoRA asks a more uncomfortable question: if a model needs the same repository context again and again, why are we paying for that knowledge as prompt tokens every time? The Code2LoRA paper proposes
05 Jun 2026 5 min read
SARDI Turns Diffusion Language Models’ Discarded Tokens Into a Retrieval Signal
ai-models

SARDI Turns Diffusion Language Models’ Discarded Tokens Into a Retrieval Signal

Most retrieval-augmented generation systems wait until the model knows what it wants to say before asking the search layer for help. SARDI flips that around in a way that feels obvious only after someone writes the paper: the words a model is not confident enough to commit may still be
05 Jun 2026 5 min read
Microsoft’s CLSA Paper Says Long-Context Models Need to Share the Routing Bill
ai-models

Microsoft’s CLSA Paper Says Long-Context Models Need to Share the Routing Bill

Long-context models keep being sold like bigger backpacks. Microsoft’s Cross-Layer Sparse Attention paper is a useful correction: the hard part is not merely carrying 128K tokens around. The hard part is paying to decide, over and over, which of those tokens deserve attention while the model is decoding the
05 Jun 2026 5 min read
Codex App 26.602 Is a Small UX Release With a Big Tell: Agents Need Observability for Humans, Too
codex

Codex App 26.602 Is a Small UX Release With a Big Tell: Agents Need Observability for Humans, Too

Codex app 26.602 is not a feature-drop headline. Good. The most revealing agent releases are often the ones that make fewer promises and sand down the places where real users get hurt: startup readiness, error reporting, usage visibility, onboarding, and the UI seams around browsers, terminals, and diffs. OpenAI’
05 Jun 2026 5 min read
GitHub Just Put Copilot Cloud Agent Behind an API. Now Your Backlog Can Call Itself.
codex

GitHub Just Put Copilot Cloud Agent Behind an API. Now Your Backlog Can Call Itself.

GitHub just made Copilot cloud agent callable infrastructure. That sounds like a small API preview until you remember what APIs do: they turn a product behavior into something scripts, internal portals, release systems, and cron jobs can invoke without a human opening the right screen and typing the right prompt.
05 Jun 2026 5 min read
← Newer Posts Page 46 of 136 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost