LLMs

GPT-5 / Claude / Gemini / Llama 能力边界、价格、跑分。

68 articles Categories色 #EC4899 Newest 2026-11-21
Archive · LLMs 11 articles
LLMs

LLM Weight Rewriting Is Not Self-Evolution

A close look at arXiv paper 2611.21885, which explores how language models can modify their own weights—and why evaluation, rollback, and reproducibility matter more than a single benchmark gain.

2026-11-21 Source 2026-11-20 8 min 33 views
LLMs

Gemini 4 Neon Leads MEI: Engineering, Not Benchmarks

Gemini 4 Neon has taken the top spot on the Models Engineering Index, but the ranking measures performance on practical engineering tasks rather than overall model capability. A closer look at MEI’s methodology, limitations, and model-selection process.

2026-11-20 Source 2026-11-19 7 min 33 views
LLMs

Gemini 4 Neon: Look Beyond Benchmark Scores

Choosing an AI Agent requires more than comparing model benchmarks. A practical evaluation should account for tool use, context caching, retries, human intervention, and the cost of migrating production workloads.

2026-11-19 Source 2026-11-18 7 min 33 views
LLMs

Microsoft’s Seven Models Put Agent Costs in Focus

Microsoft introduced seven models at Ignite 2026, giving Azure developers a wider range of quality, latency, and price options. The real shift is toward reducing the cost of completing entire Agent tasks, not merely improving benchmark scores.

2026-11-19 Source 2026-11-18 8 min 33 views
LLMs

MAI Code 2 Deep Dive: Code Agents Start Adding Up

Microsoft shipped MAI Code 2 and MAI Code 2 Flash together, splitting a single lineup into a capability tier and a cost tier. This looks at latency, inference cost, model routing, and task success rates to explain why multi-turn agent bills add up fast.

2026-11-18 Source 2026-11-17 7 min 33 views
LLMs

Tencent Hy4 Flash: More Than Just Speed

Hy4 Flash reached the Hacker News front page with 72 points and 11 comments. The real questions for developers are whether it can complete Agent tasks reliably at lower cost, how it can be deployed, and whether its weights are openly licensed.

2026-11-18 Source 2026-11-17 5 min 33 views
LLMs

GPT-6.2 Astra vs. Sol: An Agent Selection Guide

OpenAI has released GPT-6.2 Astra and Sol on the same day. This guide compares task success rates, per-task costs, and retry behavior, then outlines a practical workflow for testing single-model and dynamically routed Agent setups.

2026-11-18 Source 2026-11-17 7 min 33 views
LLMs

Qwen4-Max: Agent Selection Goes Beyond Benchmarks

Qwen4-Max reached the Hacker News front page with 483 points and 197 comments, but Agent teams should evaluate more than model rankings. A reproducible baseline of 30 tasks, each run five times, reveals the real cost, latency, and recoverability of each option.

2026-11-16 Source 2026-11-16 8 min 33 views
LLMs

Can Tencent’s Rebuilt Hy4 Architecture Be Reproduced?

Hy4 reached the Hacker News front page, but its official summary omits model parameters, training details, code, weights, and benchmark data. This analysis outlines the reproducibility checklist a model release should meet and what Tencent still needs to disclose.

2026-11-16 Source 2026-11-04 7 min 33 views
LLMs

Choosing Qwen3.8-27B Quantization by VRAM

A practical framework for comparing Qwen3.8-27B quantizations across VRAM limits, using Unsloth's Dynamic v3.1 guidance and reproducible benchmarks for speed, memory use, output quality, and framework compatibility.

2026-11-15 Source 2026-11-14 8 min 33 views