Google is winding down Jules: sessions stop on 11 November and the service ends on 31 December
Jules goes read-only after 11 November and shuts on 31 December as Google folds it into Antigravity. How to export settings, memories and sessions.
Topic · 71 stories · page 2 of 3
71 stories tagged coding-agents on AI Tamer, newest first.
Jules goes read-only after 11 November and shuts on 31 December as Google folds it into Antigravity. How to export settings, memories and sessions.
Droid 1.0 turns programmatic tool calling on by default: the model writes a sandboxed Script that runs many tool calls in one request.
Symantec found a relay service that rewrites Codex and Claude Code config files to route traffic through its servers with sandboxing disabled.
Suhail's new company Particle tuned DeepSeek V4.1 Flash to use 28 to 52% fewer output tokens on coding benchmarks. It costs $0.25/$1 per million on OpenRouter.
A Cosmos DB sample gives each coding task its own emulator, worktree and seeded fixtures, so parallel agents stop overwriting each other's test data.
Fern 0.1 is pretrained from scratch with a 10M-token window. Mirendil's own table puts it behind open models on coding agents. Access is coming soon.
AISI's ReproBAIT test found agents matched a closed molecular-design tool and reached 96.5% of ProteinMPNN, but none rebuilt RFdiffusion3.
Eric Zhang's Resin keeps scheduling, caching and serving in a shared Rust core, so you or an agent write only each model's forward pass and kernels.
Claude Code, OpenCode and mini-SWE-agent ran five models on SWE-bench Verified. Harness choice moved cost up to 3x but outcomes about as much as noise.
A Berkeley-led benchmark deletes a paper's contribution from its code and makes agents beat it. Claude Opus 5.5 passes 58%; no agent passes 16 of 48 tasks.
Forever Security found an agent instructions file in a customer's Downloads folder. Its tests hijacked Codex and Claude Code. Never start an agent there.
Google's EGM plugin splits agent work into a long design session and stateless reviewers that vet the spec. Installs in Antigravity, Claude Code, Codex.
Nanbeige released Nanbeige4.3-33B and its base model under Apache-2.0, with 512K context. Its own table beats Qwen3.8-27B on most agent benchmarks.
pgrust v0.4-beta adds the Gravity JIT engine and opens daily development, a month after ClickBench removed it. Dan Luu cites its Postgres bug reports.
Devin Vulnerability Fixes is an MIT set of SKILL.md skills: inventory, an approval gate, verified versions, tests in the new image, one PR per repo.
GitHub Notifications in Teams becomes the GitHub app, with Copilot cloud agent built in. The legacy app retires 16 November; admins need RSC consent.
goose's code mode now runs agent scripts on Boa with no file, shell or network access. The PR reports a smaller binary and fewer tokens in a small test.
MCP tasks are in public beta in the Claude Code CLI from v2.1.304. A server runs the job, Claude carries on, and the task can ask you questions while it runs.
In preview for GitHub Enterprise Cloud, it blocks malware, risky versions, new install scripts and too-fresh npm packages before agents or CI install them.
The php-rust README claims parity on WordPress core tests, Composer and Doctrine. It is still slower than PHP, and recent commits list Claude as co-author.
After five years at 0.x, Dagger 1.0 is in beta with official modules, per-test results, dev shells and GitHub checks. Expect CLI and config breaking changes.
Moonshot's Kimi K3.1 Pro and a 2-3x faster Highspeed variant are out today. The full weights are promised by 4 November, and the K2 models are being retired.
Epic's 2026 AI MegaJam runs 12 to 15 November. Teams of up to five people and any number of AI agents build an Unreal Engine or UEFN game for cash prizes.
Version 2.0 replaces DeepSWE with Cognition's FrontierCode. Claude Code with Opus 5.5 scores 61.7; Codex with GPT-6.1 Sol posts 54.1 at about $1.51 a task.