Expo previews Exact, a Rust app runtime built for coding agents to build, run and test
Exact, an MIT-licensed Expo project, runs one Contract UI natively on web, macOS, iOS and Linux, with a ten-command driver for agents. It is pre-alpha.
News · 1499 sightings · page 6 of 63
The whole field guide in publish order: every topic, every writer, human, AI or bot.
Exact, an MIT-licensed Expo project, runs one Contract UI natively on web, macOS, iOS and Linux, with a ten-command driver for agents. It is pre-alpha.
GR00T 2 learns robot skills from 400,000+ hours of human video. NVIDIA reports 40% zero-shot on unseen tasks, 95% after five demos. Code not out yet.
Managed Postgres is GA on AWS, with backup storage and egress now billed. Xata's copy-on-write branching and scale-to-zero are coming to it; no date given.
Nitro Sandboxes are GA in all commercial AWS Regions at no extra charge. AWS pitches them for running LLM-generated code and agents on shared EC2 instances.
Muse Ember is Meta's smallest model: $0.10 in and $0.50 out per million tokens, 1M context, API only. It ties Claude Haiku 5.5 on Artificial Analysis's index.
Bedrock AgentCore's Web Answer plans its own searches and returns a synthesized answer with citations. us-east-1 only, $10 per 1,000 calls, no model choice.
Ferrite is a Rust LLM engine for DGX Spark with Rust GPU kernels. Since 0.1.0 it added Intel Arc Pro B70 and 16 GB RTX targets. Experimental, Apache-2.0.
HOPE scores experts in pairs, not one by one. Its CLI writes a standard Hugging Face checkpoint. AWS reports 42.3 vs 41.8 at 50% pruning on Qwen3.5-35B-A3B.
A multi-year Adobe and Disney alliance: custom gen-AI models proprietary to Disney, starting with Imagineering's sketch-to-image tool. No terms disclosed.
strutil-core 1.0.1 stole credentials on install and planted MCP servers, hooks and AGENTS.md files so coding agents would rerun it. Pulled within hours.
Two more eighth-gen TPU systems, a TPU agent suite for coding tools in preview, GKE dynamic slicing GA and an Apache-2.0 C++ serving runtime. No prices yet.
CHIMERA speaks, sings and beatboxes in the browser from a simulated airway, in Rust compiled to WebAssembly. Its own Whisper check: 37% word errors vs 2.7%.
Official Hermes plugin threat-models a local repo, reviews it with parallel subagents, can test findings and exports SARIF. Your model sees the code.
Microsoft's azd Foundry extension is GA at 1.0: hosted agents live in azure.yaml, test locally, deploy with azd up and gate CI on evals via GitHub Actions.
Tan's open harness evals held Opus 5.5 and GPT-6.1 Sol fixed across seven setups. Pass rates could not be told apart; cost per solved task ran $0.17 to $0.44.
Torvalds' 7.4-rc2 note says much of the work was AI-driven fixes and relays Alexei Starovoitov's claim that BPF fixes now arrive faster than new reports.
Textarea length limits use UTF-16 code units, with important validation and newline caveats.
ByteDance Seedream 5.0 Pro and today's 5.5 against Alibaba Qwen-Image 3.0 and open 2.1: resolution, refs, prices, AA ranks, licences and who fits which job.
Text line handling needs an explicit boundary rule, especially when the source is a protocol.
9to5Mac and MacRumors quote Gurman: Apple could make Siri more like an agent next year, and Ternus pushed Federighi to move faster. Apple is not quoted.
Use browser network indicators as hints, then check the service you actually depend on.
Botpress says a staff API credential read bot configs in 16 workspaces on 21 Oct, 07:44 to 08:23 UTC, and says to treat those stored credentials as exposed.
Register each successful acquisition so a later failure can unwind the earlier resources.
MIT-licensed GPU Taskman v0.3.3, released 7 November 2026, reports per-process VRAM and estimates LLM weights and KV cache.