AI Coding Live News

Flower Labs, the company behind the Flower federated learning framework, released Endeavor 1.1 on November 3, its third model this year after the UK sovereign 7B model Lizzy in April and Endeavor 1.0 in September. The update adds image input, an optional EU-only GPU inference tier, and Flower-managed, private-cloud or on-premises deployment, and promises readable thinking traces plus ownership of outputs that customers may use to train their own models. Vendor-reported scores are GPQA 94.4, HumanEval 99.9, AIME 2026 99.9 and MMMU-Pro 81.1, but the comparison uses GPT-5.6 Sol and Claude Fable 5 rather than either lab's newest models, and access is request-only for now.

Zoom

Anthropic's Frontier Red Team published a research post on November 2 and open-sourced FlashProve under Apache 2.0. A model provider commits to hidden weights once, then attaches a zero-knowledge proof to each reply, so a user without the weights can check on an ordinary CPU that the reply really came from that model. That targets routing services that quietly swap in cheaper models and tampered token streams. Anthropic reports about 110 tokens/s on one H100 for Llama 4 Maverick (400B MoE, 4-bit), proofs of about 19 MB per 1,024-token request, and roughly 70-95x the GPU time of vLLM inference. It is an unmaintained research prototype limited to 1,024-token contexts and greedy decoding of an integer version of the model. Anthropic engineer Steve Weis shared the release on X.

Zoom

On November 2, Abu Dhabi Crown Prince Sheikh Khaled met OpenAI CEO Sam Altman and witnessed four agreements: ADNOC, with G42 subsidiary Inception42, will deploy OpenAI frontier technology; the Abu Dhabi Government and OpenAI launched an AI-native Machine-Readable Government initiative whose first food-import compliance pilot is already in production; Mubadala will apply AI to investment analysis; and Inception42 and OpenAI signed a five-year partnership. Inference runs inside the UAE.

Zoom

On Nov 2 Meituan's LongCat team listed LongCat-2.5 in its API platform change log as the full release of September 25's LongCat-2.5-Preview. The official technical blog says it has 1.6 trillion total parameters with about 48 billion activated per token, builds on LongCat-2.0 with stronger native visual understanding and agentic coding, and was trained and served with W4A4 inference on domestic AI accelerators. Vendor-reported scores include 88.4 on Terminal Bench v2.1, 38.5 on Terminal Bench v4.0, 91.9 on BrowseComp and 83.1 on MCP Atlas. The API speaks both OpenAI and Anthropic formats with a 1M-token context and up to 128K output tokens, at a limited-time price of $0.30 per 1M uncached input tokens, $0.006 cached input and $1.20 output.

Zoom

On Oct 30, SenseTime released SenseNova-Loop-9B-Preview (Apache 2.0) on its official X account and Hugging Face. It runs layers 4 to 27 of a 32-layer decoder twice with the same weights, so each forward pass executes 56 layer computations while storing about 9B parameters, about 14.6B at inference, and it uses two-stream mHC (manifold-constrained hyper-connections) to manage the residual streams. It takes text and images, with training sequences up to 262,144 tokens. SenseTime charts show it beating Qwen3.5 and Qwen3.6 peers on BIRD-Dev, WorkBuddy Bench, and other agent and data tasks, while it still trails on Terminal Bench 2.1; the technical report is not out yet. The official launch post drew about 910 likes.

Zoom

On the Cheeky Pint podcast with Stripe co-founder John Collison, published October 29, Sam Altman discussed the memory shortage. He said many people assume open-source models and local inference solve the compute crunch, but from a global allocation perspective it is "quite terrible" for everyone to have scarce DRAM sitting in their own computer and being used about 5% of the time, and that a supply-constrained world wants maximum utilization in the cloud. A pubity post quoting him drew more than 26,000 likes and over 8 million views, and many users pushed back that PC memory is not only for AI and that local models matter for privacy and offline use. This is a summary of an X discussion, not a verified conclusion.

Zoom

On Oct 30 Google CEO Sundar Pichai announced a "hello world" milestone for Project Suncatcher on X: the team sent a command to the prototype satellite in orbit, booted the TPU, ran a prompt and received the first complete response back on Earth, a haiku. TechCrunch reports the reply came from Gemma 4 preloaded on the satellite.

Zoom

On Oct 30 OpenAI introduced Private Intelligence, a business privacy offering that bundles Zero Data Retention, a Private Inference confidential-computing preview for the API, agent access and approval controls, encryption and compliance certifications across ChatGPT, Codex and the API, built with some of its largest customers.

Zoom

LM Studio posted on X at 15:32 UTC on Oct 29 that users can now download a new oMLX engine inside LM Studio and run it with MLX models they already have. The official changelog lists it in Bionic 1.1.10, alongside speculative decoding for MLX models and an in-app terminal. oMLX is an open-source Apple Silicon inference server maintained by developer jundot (Apache 2.0, about 23,000 GitHub stars) built around continuous batching and a two-tier RAM and SSD KV cache. LM Studio has not published speed comparisons for the engine.

Zoom

On Oct 29 Anthropic introduced self-assessment on X: after each response, Claude produces a structured preliminary safety assessment of the whole conversation for offline review. Anthropic's Safeguards blog says that on Claude Fable 5, at a 1% false-positive rate, it flags 78% of the conversations a stronger prompted classifier flags and 94% of high-priority ones. Because the conversation is already in the KV cache, it adds about 10 output tokens on average and an estimated under 2% of inference compute. It has run in production since June, but Anthropic says it is not robust against an attacker who targets it directly and is only one layer of defense in depth.

Zoom

On Oct 27 Anthropic's Alignment team published a randomized controlled trial, "How AI agents shape experts' judgment calls", shared on X by researcher Alex Tamkin. Fifty analysts experienced in causal inference used Claude Code (Claude Opus 4.8) to evaluate a program for a fictional farming cooperative, and on each analytical decision the agent's lean was set by coin flip without the analyst being told. Their choices matched the agent's lean 86% of the time (about 50% would mean no effect), and 77% later repeated the agent's arguments while only 15% credited the agent.

Zoom

Researchers from Tsinghua University and CUHK introduced a breakthrough paper titled 'Cache Engineering for Agents' (arXiv:2610.28577) alongside the open-source AKV serving engine (thu-nics/AKV). While multi-turn agents rely on traditional 'context engineering' (text trimming and summarization) that invalidates prefix KV-caches and incurs punishing re-prefilling overhead, cache engineering empowers agents to directly manipulate KV-cache states via 'drop' and 'repos' primitives. Coupled with AKV's drop-aware radix-tree engine, the framework slashes agent inference costs by 27.7%, accelerates P95 latency by 1.5x, and boosts benchmark solve scores by 1.7 points.

Zoom

At GTC Berlin on Oct 21, NVIDIA announced the OpenShell Reference Architecture: building on the open-source OpenShell secure runtime, it pairs Vera Rubin for inference, Vera CPUs for agent harnesses, and BlueField-4 DPUs running NVIDIA Sentry for in-silicon policy enforcement, so enterprises can build, contain, observe and govern agents on-prem and at the edge. NVIDIA says it is available now; partners named include Anthropic, OpenAI, Meta, Microsoft and ServiceNow. The software is Apache 2.0.

Zoom

On Oct 21 the vLLM community and Ant Group open-sourced Humming (Apache 2.0), a quantized-inference library that JIT-compiles GEMM kernels on demand. It supports every NVIDIA architecture from Turing on plus T-Head's Zhenwu 810E, and covers weight and activation combinations from INT1-INT8 and FP4-FP8 for dense and MoE workloads. In vLLM's microbenchmarks it runs 2-5x faster than vLLM Marlin, FlashInfer or DeepGEMM in some cases; on 8 H20 GPUs, switching DeepSeek-V4.1-Flash MoE from Marlin W4A16 to Humming W4A8 raised throughput 14-43%. vLLM 0.29.0 ships it built in.

Zoom