Simon Willison on llm

584 posts tagged “llm”

LLM is my command-line tool for running prompts against Large Language Models.

2023

Open questions for AI engineering

Last week I gave the closing keynote at the AI Engineer Summit in San Francisco. I was asked by the organizers to both summarize the conference, summarize the last year of activity in the space and give the audience something to think about by posing some open questions for them to take home.

[... 6,928 words]

2:18 pm / 17th October 2023 / llm, generative-ai, my-talks, ai, llms, annotated-talks, code-interpreter, coding-agents

Release datasette-llm-embed 0.2 — Datasette plugin adding a llm_embed(model_id, text) SQL function

8th Oct 2023, 5:42 pm · llm, datasette

Release datasette-llm-embed 0.1 — Datasette plugin adding a llm_embed(model_id, text) SQL function

8th Oct 2023, 4:31 am · llm, datasette

Release datasette-llm-embed 0.1a1 — Datasette plugin adding a llm_embed(model_id, text) SQL function

8th Oct 2023, 1:36 am · datasette, llm

Weeknotes: the Datasette Cloud API, a podcast appearance and more

Datasette Cloud now has a documented API, plus a podcast appearance, some LLM plugins work and some geospatial excitement.

[... 1,243 words]

12:03 am / 1st October 2023 / llm, sqlite, datasette-cloud, journalism, ai, alex-garcia, llms, datasette, generative-ai, projects, weeknotes

Talking Large Language Models with Rooftop Ruby

I’m on the latest episode of the Rooftop Ruby podcast with Collin Donnell and Joel Drapper, talking all things LLM.

[... 15,489 words]

3:39 pm / 29th September 2023 / llm, llms, generative-ai, interviews, ai, speaking, podcasts, code-interpreter, podcast-appearances, coding-agents

Release llm-llama-cpp 0.2b1 — LLM plugin for running models using llama.cpp

28th Sep 2023, 3:22 am · llm

Finding Bathroom Faucets with Embeddings. Absolutely the coolest thing I’ve seen someone build on top of my LLM tool so far: Drew Breunig is renovating a bathroom and needed a way to filter through literally thousands of options for facet taps. He scraped 20,000 images of fixtures from a plumbing supply site and used LLM to embed every one of them via CLIP... and now he can ask for “faucets that look like this one”, or even run searches for faucets that match “Gawdy” or “Bond Villain” or “Nintendo 64”. Live demo included!

# 27th September 2023, 6:18 pm / llm, embeddings, generative-ai, ai, drew-breunig, clip

Release llm-llama-cpp 0.2b0 — LLM plugin for running models using llama.cpp

22nd Sep 2023, 3:24 am · llm

LLM 0.11. I released LLM 0.11 with support for the new gpt-3.5-turbo-instruct completion model from OpenAI.

The most interesting feature of completion models is the option to request “log probabilities” from them, where each token returned is accompanied by up to 5 alternatives that were considered, along with their scores.

# 19th September 2023, 3:28 pm / llm, projects, generative-ai, openai, ai, llms

Release llm 0.11 — Access large language models from the command-line

19th Sep 2023, 6:35 am · llm

Weeknotes: Embeddings, more embeddings and Datasette Cloud

Since my last weeknotes, a flurry of activity. LLM has embeddings support now, and Datasette Cloud has driven some major improvements to the wider Datasette ecosystem.

[... 2,427 words]

5:10 am / 17th September 2023 / sqlite-utils, llm, datasette-cloud, plugins, alex-garcia, datasette, projects, embeddings, weeknotes

Release llm-sentence-transformers 0.1.2 — LLM plugin for embeddings using sentence-transformers

13th Sep 2023, 10:38 pm · llm

Build an image search engine with llm-clip, chat with models with llm chat

LLM is my combination CLI tool and Python library for working with Large Language Models. I just released LLM 0.10 with two significant new features: embedding support for binary files and the llm chat command.

[... 1,188 words]

8:33 pm / 12th September 2023 / llm, projects, generative-ai, annotated-release-notes, ai, local-llms, llms, embeddings, clip, cli

Release llm-clip 0.1 — Generate embeddings for images and text using CLIP with LLM

12th Sep 2023, 7:17 pm · llm

Release llm 0.10 — Access large language models from the command-line

12th Sep 2023, 7:13 pm · llm

Release llm-clip 0.1a0 — Generate embeddings for images and text using CLIP with LLM

12th Sep 2023, 6:32 am · llm

Release llm 0.10a1 — Access large language models from the command-line

12th Sep 2023, 6 am · llm

Release datasette-llm-embed 0.1a0 — Datasette plugin adding a llm_embed(model_id, text) SQL function

8th Sep 2023, 9:50 pm · llm, datasette

Release llm-sentence-transformers 0.1.1 — LLM plugin for embeddings using sentence-transformers

8th Sep 2023, 8:45 pm · llm

hubcap.php (via) This PHP script by Dave Hulbert delights me. It’s 24 lines of code that takes a specified goal, then calls my LLM utility on a loop to request the next shell command to execute in order to reach that goal... and pipes the output straight into `exec()` after a 3s wait so the user can panic and hit Ctrl+C if it’s about to do something dangerous!

# 6th September 2023, 3:45 pm / llm, security, php, generative-ai, ai, llms, ai-agents

Symbex 1.4. New release of my Symbex tool for finding symbols (functions, methods and classes) in a Python codebase. Symbex can now output matching symbols in JSON, CSV or TSV in addition to plain text.

I designed this feature for compatibility with the new “llm embed-multi” command—so you can now use Symbex to find every Python function in a nested directory and then pipe them to LLM to calculate embeddings for every one of them.

I tried it on my projects directory and embedded over 13,000 functions in just a few minutes! Next step is to figure out what kind of interesting things I can do with all of those embeddings.

# 5th September 2023, 5:29 pm / symbex, llm, generative-ai, projects, ai, embeddings

Release llm 0.10a0 — Access large language models from the command-line

5th Sep 2023, 6:43 am · llm

LLM now provides tools for working with embeddings

LLM is my Python library and command-line tool for working with language models. I just released LLM 0.9 with a new set of features that extend LLM to provide tools for working with embeddings.

[... 3,521 words]