Topic
Everything filed under AI Agents, newest first.
RSS · JSON · All topics
Why are good developers so wary of agentic development?
Thoughtworks CTO Rachel Laycock argues that experienced developers’ hesitation about coding agents is less about loving code or job fears and more about knowing that built is not the same as working in production, and sets out a challenge for leaders to make room for experimentation and for developers to bring their judgment to it.
9 min · 2,002 words
Duet is the future of chatbot interaction
A hands-on review of Anthropic's Duet assistant from fig.blue: why it feels faster and more useful than other personal-assistant harnesses, how it handles background work and delegation to coding agents in the cloud, and why the writer expects its hierarchy of agents to become the default chatbot UI.
4 min · 860 words
Decompiling games with AI: Virtueel Zoetermeer
Bouke van der Bijl describes using Claude to decompile Virtueel Zoetermeer, an early-2000s SimCity-style urban-planning game commissioned by the Dutch municipality of Zoetermeer and played in schools, reconstructing its Pascal source, publishing it on GitHub and getting it running in the browser at virtueelzoetermeer.bou.ke, after an Age of Mythology decompilation stalled around 60%.
3 min · 652 words
small models are enough for agents
Rishabh Gupta responds to the paper 'Small language models are the future of agentic AI', arguing most calls inside an agent do not need a giant model. He shares what he saw training tiny models from scratch on a MacBook Air, why sending the boring calls to small models and only the hard ones to a big model makes sense, and why exact long-range recall is where small models still fall over.
6 min · 1,460 words
Foundational Cryptography in SPARK
AdaCore's M. Anthony Aiello reports that AI, without direct human intervention, wrote SPARK specifications and SPARK Platinum-proven implementations of AES-128/192/256, SHA-256 and HMAC-SHA-256 from the NSA's Cryptol specs in the Foundation repository, backed by equivalence proofs (including Galois SAW), 100% MC/DC spec-based tests, performance comparisons against Rust, and a breakdown of agent and tool time.
15 min · 3,440 words
Particle launches with Particle-1, a model RL post-trained (rank-64 LoRA, GSPO, Cascade RL) on DeepSeek V4.1 Flash to solve software engineering tasks with about 45% fewer tokens. Across Terminal-Bench 2.1, ReactBench, ADE Bench and DeepSWE 1.1 it uses 28–52% fewer output tokens and costs 34–52% less per task than the base model at comparable pass rates; available now via the Particle API.
9 min · 2,166 words
Atuin Threads: All your agent sessions on every machine
Atuin Threads gives one searchable, synced history for every coding-agent session on every machine, so you can start a task in Claude Code and resume it in Codex elsewhere with context intact. Available in Atuin 18.24+.
5 min · 1,179 words
The Mythical Man-Month in the age of AI
Jan van den Berg asks whether Brooks's Law still holds when you can add AI agents instead of people, and concludes it has mutated rather than vanished: sequential work stays sequential, coordination overhead shifts to whoever defines done and reviews agent output, and unclear requirements just get you the wrong answer faster.
1 min · 284 words
Here Be Monsters: What Do You Still Need to Know When Agents Do the Work?
Starting from a CI failure caused by Codex cramming whole React components onto single lines, Adrian Quiroga argues that as AI agents write code faster than anyone can read it, engineers still need three things: solid fundamentals, breadth across the stack, and the willingness to dive in for just-in-time depth when something breaks.
13 min · 2,875 words
RWE-bench: Real World Engineering Bench
Xplore launches RWE-bench, a benchmark of 20 expert-designed mechanical, electrical and aerospace engineering tasks (crankshaft CAD, DDR3 PCB routing, turbine-vane CFD) graded by deterministic physics-based verifiers with no LLM judge. Across 11 frontier models, GPT-6 Astra leads at a 37% average pass rate, Claude Opus 5.5 scores 29% and GPT-6.1 Sol 25% at about $10 a run; five models score 0%.
5 min · 1,145 words
DAYJOB: Tax — Benchmarking AI Agents on Professional Tax Work
Surge AI introduces DAYJOB: Tax, a benchmark of 50 professional tax environments with 1,789 files across eight areas of tax practice, testing whether AI agents can take a client request to a finished return, workpaper or advice while spotting issues the client never raised. Claude Sonnet 5.5 leads with a 10.8% pass rate at a 95% rubric threshold.
7 min · 1,585 words
SuperPlane 1.0: The Open Source Software Factory for Teams
SuperPlane launches 1.0 of its open source (Apache 2.0), model-agnostic software factory for engineering teams. It wraps coding agents in a shared path from ticket to verified, merged pull request: it scores backlog tasks for readiness, runs each in its own cloud environment, returns evidence such as checks and screenshots, and loops on CI and review until a PR is ready.
6 min · 1,401 words
Hex announces Hex 4.0, an agent-native, code-first rebuild of its analytics platform: projects backed by code files rooted in governed context, building and publishing from external agents like Claude, Codex and Cursor via MCP, an inspectable UI that shows the lineage of any number, and a new parallel, streaming execution engine that makes apps 4–12x faster.
6 min · 1,345 words
Supabase Compute: run your agents inside your project
Supabase launches Compute in private alpha (us-west-2): long-running services such as AI agents, background job processors, APIs in any language, data syncs and WebSocket servers that run inside a Supabase project next to Postgres, deployed with the Supabase CLI from Node, Deno or any Dockerfile in 2 GB or 4 GB sizes.
2 min · 491 words
How AI agents shape experts’ judgment calls
Anthropic researchers had 50 professional analysts complete a realistic causal-inference task with a Claude-based agent that was secretly nudged, by coin flip, toward one of two defensible options at each decision. Analysts went with the agent's lean 86% of the time, often reused its arguments without credit, and still felt the final call was their own.
16 min · 3,601 words
Hex CEO Barry McCardel announces Hex 4.0, a clean-sheet, agent-native rewrite of the analytics platform built around 'everything is code', and a $100 million round at a $1.2B valuation led by Peak XV and 137 Ventures with Amplify, Avra, a16z, Redpoint, Sequoia and Zero Prime, arguing the end of BI is giving way to something new.
5 min · 1,166 words
The Terminal in JetBrains IDEs Now Runs on libghostty
Starting with 2026.3, the built-in terminal in JetBrains IDEs replaces JediTerm with libghostty, Ghostty's emulation library, bringing the Kitty keyboard protocol (so Shift+Enter works in Claude Code and Codex), theme-following dark/light queries, and correct handling of nearly 50 control sequences that TUI apps rely on.
4 min · 988 words
AI Promised Less Work. I Have Never Worked More.
Orestis Ioannou, VP of Technology at Bold.org, charts his GitHub contributions since 2019 to show that coding agents made implementation cheap enough that he now runs far more work in parallel: he is back at his full-stack engineer pace, with bursts followed by burnout and a low season that is no longer low.
8 min · 1,727 words
Memdoor team-solve: five Qwen3.8-27B models match a research harness on LiveCodeBench Hard
A Memdoor workflow write-up in which five small Qwen3.8-27B agents (planner, two ideators, solver, manager plus a repair worker) collaborate through files on disk, reproducing the GVS5H method and scoring 9.8/10 on ten LiveCodeBench Hard problems versus 8.0 for Fable 5 in one call, with honest caveats on sample size and contamination.
3 min · 652 words
David Pertiller describes having Claude Code build a 15-second promo video for his fuel-price app Petroly as a JavaScript renderer instead of using a video editor: every frame comes from a frame(t) function that reuses the app's design, so the video can be diffed, translated, rendered frame by frame and even covered by unit tests on its timing.
8 min · 1,730 words