Bookmarks

#llms

50 bookmarks tagged with #llms · RSS Feed · ← All Tags

MTPLX: The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server. · GitHub

https://github.com/youssofal/MTPLX
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server. - youssofal/MTPLX
#llms #macos
archive.org #1189

Prompt Caching In Agents | EARENDIL

https://earendil.com/posts/prompt-caching/
How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.
via Armin on bs, seems he works onp pi? or created it?
#llms
archive.org #1105

GLM-4.7: Advancing the Coding Capability | Hacker News

https://news.ycombinator.com/item?id=46357287
x.ai - chinese company. model claims to be very good for coding and plans are pretty cheap. but some question if it's as good as claude opus. but worth being aware of. also cerebrus offer this model with insanely fast tokens per second that potentially allows of interesting use cases with well designed test suite and specs...
#llms
archive.org #855

Vibe engineering

https://simonwillison.net/2025/Oct/7/vibe-engineering/
I feel like vibe coding is pretty well established now as covering the fast, loose and irresponsible way of building software with AI—entirely prompt-driven, and with no attention paid to …
#llms #programming #vibe-engineering
archive.org #730

How to Fix Your Context | Drew Breunig

https://www.dbreunig.com/2025/06/26/how-to-fix-your-context.html
6 tactics for fixing your context and shipping better agents. As Karpathy says, building LLM-powered apps means learning to ‘pack the context windows just right’—smartly deploying tools, managing information, and maintaining context hygiene.
#llms #programming
archive.org #656

LLM pricing calculator

https://www.llm-prices.com/
Cost of various LLMs.
As of 2025-05-31 Gemini pro 2.5 <200k tokens is excellent value and performs similarly to Claude Sonnet 4 and 3.7 for me at most programming tasks. Sonnet 4 and Sonnet 3.7 are same price. Claude Opus 4 is v. expensive and writes loads of tests and generally overdoes things.
#llms
archive.org #634

OpenAI Is A Systemic Risk To The Tech Industry

https://www.wheresyoured.at/openai-is-a-systemic-risk-to-the-tech-industry-2/
Before we go any further: I hate to ask you to do this, but I need your help — I'm up for this year's Webbys for the best business podcast award. I know it's a pain in the ass, but can you sign up and vote for Better Offline? I have
#ai #llms
archive.org #620

Denial

https://adactio.com/journal/21831
The best of the web is under continuous attack from the technology that powers your generative “AI” tools.
#llms #miniflux
archive.org #580

AI ambivalence

https://nolanlawson.com/2025/04/02/ai-ambivalence/
I've avoided writing this post for a long time, partly because I try to avoid controversial topics these days, and partly because I was waiting to make my mind up about the current, all-consuming, conversation-dominating topic of generative AI. But Steve Yegge's "Revenge of the junior developer" awakened something in me, so let's go for…
#llms #miniflux
archive.org #574

Another study on LLM energy use

https://birchtree.me/blog/another-study-on-llm-energy-use/
This study was linked to by The Verge today, and as someone who keeps looking at the energy costs of AI wondering why he’s missing something, one of the opening lines in the study’s executive summary really caught my eye: Electricity consumption from data centres, artificial intelligence (AI)
#llms
archive.org #539

Claude 3.7 Sonnet and Claude Code

https://simonwillison.net/2025/Feb/24/claude-37-sonnet-and-claude-code/
Anthropic released **Claude 3.7 Sonnet** today - skipping the name "Claude 3.6" because the Anthropic user community had already started using that as the unofficial name for their [October update …
#llms
archive.org #514

Things we learned about LLMs in 2024

https://simonwillison.net/2024/Dec/31/llms-in-2024/
A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past …
#llms
archive.org #457

AI as a tool for teaching critical thinking: a case study | Tim Hayward

https://timhayward.wordpress.com/2024/12/18/ai-as-a-tool-for-teaching-critical-thinking-a-case-study/
As I prepare materials for a new university course on Propaganda and Censorship in Democracies, I am working on exercises intended to stretch - and hopefully fascinate - students. In this I am being assisted by Claude AI which acts as an unflaggingly obliging soundboard for ideas, whether in the form of inchoate hunches or…
#llms
archive.org #439

Aider

https://simonwillison.net/2024/Jul/31/aider/
Aider is an impressive open source local coding chat assistant terminal application, developed by Paul Gauthier (founding CTO of [Inktomi](https://en.wikipedia.org/wiki/Inktomi) back in [1996-2000](https://www.linkedin.com/in/paulgauthier/details/experience/)). I tried it out today, using an …
#llms #programming
archive.org #233

GitHub - Doriandarko/claude-engineer: Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capabilities of a large language model with practical file system operations and web search functionality.

https://github.com/Doriandarko/claude-engineer
Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capabilities of a large language model with practical file system operations and web search functionality. - Doriandarko/claude-engineer
#llms #programming
archive.org #216

Open challenges for AI engineering

https://simonwillison.net/2024/Jun/27/ai-worlds-fair/#slide.014.jpeg
I gave the opening keynote at the AI Engineer World’s Fair yesterday. I was a late addition to the schedule: OpenAI pulled out of their slot at the last minute, …
#llms
archive.org #215