World Wire

Z.ai just released GLM-5.3 . GLM-5.3 runs on the same 743B base model as GLM-5.2 . Every reported gain comes from scaled post-training: more task environments, more environment types, longer training. The results land in two places. Coding jumps most on the longest-horizon benchmarks, with Terminal-Bench 3.0 moving from 4.6 to 28.3. Cybersecurity moved further than Z.ai says it expected, with CyberGym reaching 84.5%. Weights are not public yet. Is It Deployable? Partially , GLM-5.3 is live through the Z.ai API , the GLM Coding Plan, and ZCode. Weights are not out. Z.ai says it will publish them roughly two weeks after launch, once safety evaluation and hardening finish. Which companies can move now : Startups and mid-market engineering orgs can adopt it today via the Coding Plan or API. Enterprises with data-residency or vendor-review rules should wait for weights. Security vendors and MSSPs get the most signal, and the most policy exposure. Industries : Developer too...

Cactus Compute has released Needle 2 , an open 45M-parameter model for tool calling, device use, and structured extraction. The entire model ships as a single 14MB binary that runs a full session in about 28MB of RAM. Weights are trained and deployed at CQ2-bit using Cactus Quants, and the model is sealed inside the company’s own C++ engine, so there is no runtime to install and no download at inference time. Reported decode throughput is 500 tokens/sec on a Raspberry Pi 5, 400–1,500 tokens/sec on Meta Quest 3S and Apple Vision Pro, and 300–700 tokens/sec on sub-$200 phones. The design premise is narrow and stated plainly by the team: mapping a messy sentence onto a typed function signature needs no world knowledge and no open-ended prose. That framing is why 45M parameters are enough here, and why the model targets hardware with no GPU and no NPU. Is it deployable? Yes, Needle 2 ships as prebuilt binaries and a static library for macOS, Linux (x86-64, ARM64, ARMv7, RIS...

In this tutorial, we build an end-to-end workflow for working with the SupraLabs reasoning corpus . We stream a representative subset directly from the Hugging Face Hub, inspect its source distribution, token-length patterns, task composition, and reasoning-to-answer ratios, and then apply a series of quality filters to remove unsuitable training examples. We transform the retained samples into a chat-based supervised fine-tuning format with explicit <think> reasoning tags and use them to adapt SmolLM2-135M-Instruct with LoRA through TRL’s SFTTrainer. By combining scalable data access, exploratory analysis, dataset curation, parameter-efficient fine-tuning, structured inference, and Parquet export, we create a complete Google Colab pipeline for turning a large multi-model reasoning corpus into a compact reasoning-focused language model. Copy Code Copied Use a different Browser import subprocess, sys def pip_install(pkgs): subprocess.check_call([sys.executable, "-m...

Google has released Gemini 3.7 Flash , the newest model in its Flash tier, three weeks after Gemini 3.6 Flash. The model card describes it as a refinement of 3.6 Flash with algorithmic improvements to the core reasoning foundation — not a new pretraining run. It accepts text, images, audio, and video across a 1M-token context window, returns up to 64K output tokens, and supports customizable thinking configurations that trade quality against cost and latency. The knowledge cutoff stays at March 2026. The gains concentrate in three places: software engineering, document-heavy knowledge work, and web development. The sharper argument is price. Gemini 3.7 Flash ships at $0.75 per 1M input tokens and $3.75 per 1M output tokens — half the original 3.6 Flash list rate, and roughly a third the blended cost of Claude Sonnet 5 or GPT-5.6 Terra. Is it Deployable? Yes, API and enterprise only. There are no open weights. Access runs through hosted surfaces: the Gemini API and Google AI...