AIQB
TutorialsOrdinary

Every new model has a 1M-token context window. Do you still need retrieval?

Source: DEV Community·
DeepSeekKimi

Summary

Look at the model releases from October alone: DeepSeek V4.1 Flash, MiniMax M3.1 Flash, Kimi K3.1...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-1ec21872655875da49475488
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Export ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Qwen chats to Markdown with Convolvger 0.6.0
If you have ever tried to export a ChatGPT conversation to Markdown, or save a Claude chat as a .md...
Source: DEV Community · ChatGPT / DeepSeek / Qwen
TutorialsOrdinary
How I built an opt-in Modal (DeepSeek) provider for my desktop AI companion — then benchmarked it and kept the old one
How I built an opt-in Modal (DeepSeek) provider for my desktop AI companion — then...
Source: DEV Community · DeepSeek
TutorialsOrdinary
The model page said 8-bit. The checkpoint is 4.49 bits per parameter.
I was working out how much disk Kimi K3.1 Pro would need, and the model page gave me two numbers that...
Source: DEV Community · Kimi
TutorialsOrdinary
DeepSeek Harness Creator Mode: When the Agent Builds Its Own Plugins — and Why That Needs Guardrails
On 2 November 2026, DeepSeek's Harness team announced Creator Mode for DeepSeek Harness, its...
Source: DEV Community · DeepSeek
TutorialsOrdinary
I built a local engine to give Web AIs hands (and no, it doesn't use APIs)
A super lightweight local engine that gives Web AIs (DeepSeek, ChatGPT) hands to execute actions on your PC. No APIs, no tokens, 100% local.
Source: DEV Community · ChatGPT / DeepSeek
TutorialsOrdinary
How to stop prompt injections and AI hallucinations at the OS level (CBS v1.6.2 release)
Disclosure: I am the author of Cyber-Butler-Security (CBS). If you run AI Agents (like DeepSeek...
Source: DEV Community · DeepSeek
TutorialsOrdinary
DeepSeek's Super-agent Defaults to Observe Mode, but Its Workers Get Full Access as You
DeepSeek open-sourced Super-agent, a GitHub coding agent. Unasked work defaults to observe mode, and its workers run with full access as your OS user.
Source: DEV Community · DeepSeek
TutorialsOrdinary
SGLang Runs DeepSeek's Own Benchmarks Against DeepInfer and Matches It
TL;DR DeepInfer is the inference engine DeepSeek built and runs behind its own service,...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Kimi K3.1 Pro: 104B active parameters still carry a 2.8T backpack
The small number in an MoE announcement is tempting. Kimi K3.1 Pro lists 2.8 trillion total...
Source: DEV Community · Kimi
TutorialsOrdinary
DeepSeek V4.1 Flash on 8 B300: vLLM vs DeepInfer, 600K+ tokens/s
DeepSeek has open-sourced DeepInfer, the engine behind its own production service. We put it head to...
Source: DEV Community · DeepSeek