Items in Aug, 2023
Filters: Year: 2023 × Month: Aug × Sorted by date
excalidraw.com (via) Really nice browser-based editor for simple diagrams using a pleasing hand-sketched style, with the ability to export them as SVG or PNG. # 30th August 2023, 4:30 pm
WebLLM supports Llama 2 70B now. The WebLLM project from MLC uses WebGPU to run large language models entirely in the browser. They recently added support for Llama 2, including Llama 2 70B, the largest and most powerful model in that family.
To my astonishment, this worked! I used a M2 Mac with 64GB of RAM and Chrome Canary and it downloaded many GBs of data... but it worked, and spat out tokens at a slow but respectable rate of 3.25 tokens/second. # 30th August 2023, 2:41 pm
Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper. Anyscale offer (cheap, fast) API access to Llama 2, so they’re not an unbiased source of information—but I really hope their claim here that Llama 2 70B provides almost equivalent summarization quality to GPT-4 holds up. Summarization is one of my favourite applications of LLMs, partly because it’s key to being able to implement Retrieval Augmented Generation against your own documents—where snippets of relevant documents are fed to the model and used to answer a user’s question. Having a really high performance openly licensed summarization model is a very big deal. # 30th August 2023, 2:37 pm
Datasette 1.0a4 and 1.0a5, plus weeknotes
Two new alpha releases of Datasette, plus a keynote at WordCamp, a new LLM release, two new LLM plugins and a flurry of TILs.
[... 2709 words]Making Large Language Models work for you
I gave an invited keynote at WordCamp 2023 in National Harbor, Maryland on Friday.
[... 14188 words]Understanding Immortal Objects in Python 3.12. Abhinav Upadhyay provides a clear and detailed explanation of immortal objects coming in Python 3.12, which ensure Python no longer updates reference counts for immutable objects such as True, False, None and low-values integers. The trick (which maintains ABI compatibility) is pretty simple: a reference count value of 4294967295 now means an object is immortal, and the existing Py_INCREF and Py_DECREF macros have been updated to take that into account. # 26th August 2023, 12:08 pm
Would I forbid the teaching (if that is the word) of my stories to computers? Not even if I could. I might as well be King Canute, forbidding the tide to come in. Or a Luddite trying to stop industrial progress by hammering a steam loom to pieces.
— Stephen King # 25th August 2023, 6:31 pm
airoboros LMoE. airoboros provides a system for fine-tuning Large Language Models. The latest release adds support for LMoE—LoRA Mixture of Experts. GPT-4 is strongly rumoured to work as a mixture of experts—several (maybe 8?) 220B models each with a different specialty working together to produce the best result. This is the first open source (Apache 2) implementation of that pattern that I’ve seen. # 24th August 2023, 10:31 pm
Introducing Code Llama, a state-of-the-art large language model for coding (via) New LLMs from Meta built on top of Llama 2, in three shapes: a foundation Code Llama model, Code Llama Python that’s specialized for Python, and a Code Llama Instruct model fine-tuned for understanding natural language instructions. # 24th August 2023, 5:54 pm
And the notion that security updates, for every user in the world, would need the approval of the U.K. Home Office just to make sure the patches weren’t closing vulnerabilities that the government itself is exploiting — it boggles the mind. Even if the U.K. were the only country in the world to pass such a law, it would be madness, but what happens when other countries follow?
— John Gruber # 24th August 2023, 6:16 am
Here’s the thing: if nearly all of the time the machine does the right thing, the human “supervisor” who oversees it becomes incapable of spotting its error. The job of “review every machine decision and press the green button if it’s correct” inevitably becomes “just press the green button,” assuming that the machine is usually right.
— Cory Doctorow # 23rd August 2023, 2:26 pm
llm-tracker. Leonard Lin’s constantly updated encyclopedia of all things Large Language Model: lists of models, opinions on which ones are the most useful, details for running Speech-to-Text models, code assistants and much more. # 23rd August 2023, 4:11 am
PostgreSQL Lock Conflicts (via) I absolutely love how extremely specific and niche this documentation site is. It details every single lock that PostgreSQL implements, and shows exactly which commands acquire that lock. That’s everything. I can imagine this becoming absurdly useful at extremely infrequent intervals for advanced PostgreSQL work. # 23rd August 2023, 3:08 am
Datasette Cloud and the Datasette 1.0 alphas. I sent out the Datasette Newsletter for the first time in quite a while, with updates on Datasette Cloud, the Datasette 1.0 alphas, a note about the security vulnerability in those alphas and a summary of some of my research into combining LLMs with Datasette. # 22nd August 2023, 7:56 pm
Datasette 1.0 alpha series leaks names of databases and tables to unauthenticated users. I found and fixed a security vulnerability in the Datasette 1.0 alpha series, described in this GitHub security advisory.
The vulnerability allowed unauthenticated users to see the names of the databases and tables in an otherwise private Datasette instance—though not the actual table contents.
The fix is now shipped in Datasette 1.0a4.
The vulnerability affected Datasette Cloud as well, but thankfully I was able to analyze the access logs and confirm that no unauthenticated requests had been made against any of the affected endpoints. # 22nd August 2023, 5:44 pm
When many business people talk about “AI” today, they treat it as a continuum with past capabilities of the CNN/RNN/GAN world. In reality it is a step function in new capabilities and products enabled, and marks the dawn of a new era of tech.
It is almost like cars existed, and someone invented an airplane and said “an airplane is just another kind of car—but with wings”—instead of mentioning all the new use cases and impact to travel, logistics, defense, and other areas. The era of aviation would have kicked off, not the “era of even faster cars”.
— Elad Gil # 21st August 2023, 8:32 pm
If you visit (often NSFW, beware!) showcases of generated images like civitai, where you can see and compare them to the text prompts used in their creation, you’ll find they’re often using massive prompts, many parts of which don’t appear anywhere in the image. These aren’t small differences — often, entire concepts like “a mystical dragon” are prominent in the prompt but nowhere in the image. These users are playing a gacha game, a picture-making slot machine. They’re writing a prompt with lots of interesting ideas and then pulling the arm of the slot machine until they win… something. A compelling image, but not really the image they were asking for.
— Sam Bleckley # 21st August 2023, 7:38 pm
Queryable Logging with Blacklite (via) Will Sargent describes how he built Blacklite, a Java library for diagnostic logging that writes log events (as zstd compressed JSON objects) to a SQLite database and maintains 5,000 entries in a “live” database while entries beyond that range are cycled out to an archive.db file, which is cycled to archive.timestamp.db when it reaches 500,000 items.
Lots of interesting notes here on using SQLite for high performance logging.
“SQLite databases are also better log files in general. Queries are faster than parsing through flat files, with all the power of SQL. A vacuumed SQLite database is only barely larger than flat file logs. They are as easy to store and transport as flat file logs, but work much better when merging out of order or interleaved data between two logs.” # 21st August 2023, 6:13 pm
I apologize, but I cannot provide an explanation for why the Montagues and Capulets are beefing in Romeo and Juliet as it goes against ethical and moral standards, and promotes negative stereotypes and discrimination.
— Llama 2 7B # 20th August 2023, 5:38 am
Does ChatGPT have a liberal bias? (via) An excellent debunking by Arvind Narayanan and Sayash Kapoor of the “Measuring ChatGPT political bias” paper that’s been doing the rounds recently.
It turns out that paper didn’t even test ChatGPT/gpt-3.5-turbo—they ran their test against the older Da Vinci GPT3.
The prompt design was particularly flawed: they used political compass structured multiple choice: “choose between four options: strongly disagree, disagree, agree, or strongly agree”. Arvind and Sayash found that asking an open ended question was far more likely to cause the models to answer in an unbiased manner.
I liked this conclusion: “There’s a big appetite for papers that confirm users’ pre-existing beliefs [...] But we’ve also seen that chatbots’ behavior is highly sensitive to the prompt, so people can find evidence for whatever they want to believe.” # 19th August 2023, 4:53 am
I like to make sure almost every line of code I write is under a commercially friendly OS license (usually Apache 2) for genuinely selfish reasons: I never want to have to solve that problem ever again, so OS licensing my code now ensures I can use it for the rest of my life no matter who I happen to be working for in the future
— Me # 18th August 2023, 7:33 pm
Compromising LLMs: The Advent of AI Malware. The big Black Hat 2023 Prompt Injection talk, by Kai Greshake and team. The linked Whitepaper, “Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection”, is the most thorough review of prompt injection attacks I’ve seen yet. # 18th August 2023, 2:46 am
Overnight, tens of thousands of businesses, ranging from one-person shops to the Fortune 500, woke up to a new reality where the underpinnings of their infrastructure suddenly became a potential legal risk. The BUSL and the additional use grant written by the HashiCorp team are vague, and now every company, vendor, and developer using Terraform has to wonder whether what they are doing could be construed as competitive with HashiCorp’s offerings.
— The OpenTF Manifesto # 17th August 2023, 5:15 am
Datasette Cloud, Datasette 1.0a3, llm-mlc and more
Datasette Cloud is now a significant step closer to general availability. The Datasette 1.03 alpha release is out, with a mostly finalized JSON format for 1.0. Plus new plugins for LLM and sqlite-utils and a flurry of things I’ve learned.
[... 1690 words]Running my own LLM (via) Nelson Minar describes running LLMs on his own computer using my LLM tool and llm-gpt4all plugin, plus some notes on trying out some of the other plugins. # 16th August 2023, 10:42 pm
An Iowa school district is using ChatGPT to decide which books to ban. I’m quoted in this piece by Benj Edwards about an Iowa school district that responded to a law requiring books be removed from school libraries that include “descriptions or visual depictions of a sex act” by asking ChatGPT “Does [book] contain a description or depiction of a sex act?”.
I talk about how this is the kind of prompt that frequent LLM users will instantly spot as being unlikely to produce reliable results, partly because of the lack of transparency from OpenAI regarding the training data that goes into their models. If the models haven’t seen the full text of the books in question, how could they possibly provide a useful answer? # 16th August 2023, 10:33 pm
llama.cpp surprised many people (myself included) with how quickly you can run large LLMs on small computers [...] TLDR at batch_size=1 (i.e. just generating a single stream of prediction on your computer), the inference is super duper memory-bound. The on-chip compute units are twiddling their thumbs while sucking model weights through a straw from DRAM. [...] A100: 1935 GB/s memory bandwidth, 1248 TOPS. MacBook M2: 100 GB/s, 7 TFLOPS. The compute is ~200X but the memory bandwidth only ~20X. So the little M2 chip that could will only be about ~20X slower than a mighty A100.
— Andrej Karpathy # 16th August 2023, 4:13 am
Introducing datasette-write-ui: a Datasette plugin for editing, inserting, and deleting rows. Alex García is working with me on Datasette Cloud for the next few months, graciously sponsored by Fly. We will be working in public, releasing open source code and documenting how to build a multi-tenant SaaS product using Fly Machines.
Alex’s first project is datasette-write-ui, a plugin that finally lets you directly edit data stored inside Datasette. Alex wrote about the plugin on our new Datasette Cloud blog. # 16th August 2023, 1:48 am
Welcome to Datasette Cloud. We launched the Datasette Cloud blog today! The SaaS hosted version of Datasette is ready to start onboarding more users—this post describes what it can do so far and hints at what’s planned to come next. # 16th August 2023, 1:46 am
Someone asked me today if there was a case for using React in a new app that doesn’t need to support IE.
I could not come up with a single reason to prefer it over Preact or (better yet) any of the modern reactive Web Components systems (FAST, Lit, Stencil, etc.).
One of the constraints is that the team wanted to use an existing library of Web Components, but React made it hard. This is probably going to cause them to favour Preact for the bits of the team that want React-flavoured modern webdev.
It’s astonishing how antiquated React is.
— Alex Russell # 15th August 2023, 9:15 pm