feedle

For the past two and a half years the feature I've most wanted from LLMs is the ability to take on search-based research tasks on my behalf. We saw the first glimpses of this back in early 2023, with Perplexity (first launched December 2022, first prompt leak in January 2023) and then the GPT-4 powe...

Gemma 3 QAT Models Interesting release from Google, as a follow-up to Gemma 3 from last month: To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training (QAT) that dramatically reduces memory requirements while maintaining high quality. This enab...

Max Woolf pointed out this new feature of the Gemini 2.5 series (here's my coverage of 2.5 Pro and 2.5 Flash) in a comment on Hacker News: One hidden note from Gemini 2.5 Flash when diving deep into the documentation: for image inputs, not only can the model be instructed to generated 2D bounding bo...

Start building with Gemini 2.5 Flash Google Gemini's latest model is Gemini 2.5 Flash, available in (paid) preview as gemini-2.5-flash-preview-04-17. Building upon the popular foundation of 2.0 Flash, this new version delivers a major upgrade in reasoning capabilities, while still prioritizing speed...

In the two and a half years that we've been talking about prompt injection attacks I've seen alarmingly little progress towards a robust solution. The new paper Defeating Prompt Injections by Design from Google DeepMind finally bucks that trend. This one is worth paying attention to. If you're new t...

LLM pricing calculator (updated) I updated my LLM pricing calculator this morning (Claude transcript) to show the prices of various hosted models in a sorted table, defaulting to lowest price first. Amazon Nova and Google Gemini continue to dominate the lower end of the table. The most expensive mod...

An LLM Query Understanding Service Doug Turnbull recently wrote about how all search is structured now: Many times, even a small open source LLM will be able to turn a search query into reasonable structure at relatively low cost. In this follow-up tutorial he demonstrates Qwen 2-7B running in a GPU...

Gemini 2.5 Pro Preview pricing Google's Gemini 2.5 Pro is currently the top model on LM Arena and, from my own testing, a superb model for OCR, audio transcription and long-context coding. You can now pay for it! The new gemini-2.5-pro-preview-03-25 model ID is priced like this: Prompts less than 20...

I was there at the first Atom meeting at the Google offices. We meant so well! And I think the basic publishing spec is good, certainly better technically than the pastiche of different things called RSS. Alas, a bunch of things then went wrong. Feeds started losing market share. Facebook started do...

Function calling with Gemma Google's Gemma 3 model (the 27B variant is particularly capable, I've been trying it out via Ollama) supports function calling exclusively through prompt engineering. The official documentation describes two recommended prompts - both of them suggest that the tool definit...

There's a new release from Google Gemini this morning: the first in the Gemini 2.5 series. Google call it "a thinking model, designed to tackle increasingly complex problems". It's already sat at the top of the LM Arena leaderboard, and from initial impressions looks like it may deserve that top spo...

suitenumerique/docs New open source (MIT licensed) collaborative text editing web application, similar to Google Docs or Notion, notable because it's a joint effort funded by the French and German governments and "currently onboarding the Netherlands". It's built using Django and React: Docs is buil...

Google's Gemma team released an impressive new model today (under their not-open-source Gemma license). Gemma 3 comes in four sizes - 1B, 4B, 12B, and 27B - and while 1B is text-only the larger three models are all multi-modal for vision: Gemma 3 introduces multimodality, supporting vision-language ...

State-of-the-art text embedding via the Gemini API Gemini just released their new text embedding model, with the snappy name gemini-embedding-exp-03-07. It supports 8,000 input tokens - up from 3,000 - and outputs vectors that are a lot larger than their previous text-embedding-004 model - that one ...

Career Update: Google DeepMind -> Anthropic Nicholas Carlini (previously) on joining Anthropic, driven partly by his frustration at friction he encountered publishing his research at Google DeepMind after their merge with Google Brain. His area of expertise is adversarial machine learning. The recen...

Gemini 2.0 Flash and Flash-Lite Gemini 2.0 Flash-Lite is now generally available - previously it was available just as a preview - and has announced pricing. The model is $0.075/million input tokens and $0.030/million output - the same price as Gemini 1.5 Flash. Google call this "simplified pricing"...

Introducing Perplexity Deep Research Perplexity become the third company to release a product with "Deep Research" in the name. Google's Gemini Deep Research: Try Deep Research and our new experimental model in Gemini, your AI assistant on December 11th 2024 OpenAI's ChatGPT Deep Research: Introduci...

Gemini 2.0 is now available to everyone Big new Gemini 2.0 releases today: Gemini 2.0 Pro (Experimental) is Google's "best model yet for coding performance and complex prompts" - currently available as a free preview. Gemini 2.0 Flash is now generally available. Gemini 2.0 Flash-Lite looks particula...

Basically any resource on a difficult subject—a colleague, Google, a published paper—will be wrong or incomplete in various ways. Usefulness isn’t only a matter of correctness. For example, suppose a colleague has a question she thinks I might know the answer to. Good news: I have some intuition and...

How we estimate the risk from prompt injection attacks on AI systems The "Agentic AI Security Team" at Google DeepMind share some details on how they are researching indirect prompt injection attacks. They include this handy diagram illustrating one of the most common and concerning attack patterns,...

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 twelve months, plus my attempt at identifying key themes and pivotal moments. This is a sequel to my review of 2023. In this article: The GPT-4 barri...

Google search hallucinates Encanto 2 Jason Schreier on Bluesky: I was excited to tell my kids that there's a sequel to Encanto, only to scroll down and learn that Google's AI just completely made this up I just replicated the same result by searching Google for encanto 2. Here's what the "AI overvie...

Finally, a replacement for BERT: Introducing ModernBERT BERT was an early language model released by Google in October 2018. Unlike modern LLMs it wasn't designed for generating text. BERT was trained for masked token prediction and was generally applied to problems like Named Entity Recognition or ...

I had big plans for December: for one thing, I was hoping to get to an actual RC of Datasette 1.0, in preparation for a full release in January. Instead, I've found myself distracted by a constant barrage of new LLM releases. On December 4th Amazon introduced the Amazon Nova family of multi-modal mo...

Those new model releases just keep on flowing. Today it's Google's snappily named gemini-2.0-flash-thinking-exp, their first entrant into the o1-style inference scaling class of models. I posted about a great essay about the significance of these just this morning. From the Gemini model documentatio...

Veo 2 Google's text-to-video model, now available via waitlisted preview. I got through the waitlist and tried the same prompt I ran against OpenAI's Sora last week: A pelican riding a bicycle along a coastal path overlooking a harbor It generated these four videos: Here's the larger video. Via Hack...

<model-viewer> Web Component by Google I learned about this Web Component from Claude when looking for options to render a .glb file on a web page. It's very pleasant to use: <model-viewer style="width: 100%; height: 200px" src="https://static.simonwillison.net/static/cors-allow/2024/a-pelican-rid...

googleapis/python-genai Google released this brand new Python library for accessing their generative AI models yesterday, offering an alternative to their existing generative-ai-python library. The API design looks very solid to me, and it includes both sync and async implementations. Here's an asyn...

Huge announcment from Google this morning: Introducing Gemini 2.0: our new AI model for the agentic era. There's a ton of stuff in there (including updates on Project Astra and the new Project Mariner), but the most interesting pieces are the things we can start using today, built around the brand n...

New Gemini model: gemini-exp-1206 Google's Jeff Dean: Today’s the one year anniversary of our first Gemini model releases! And it’s never looked better. Check out our newest release, Gemini-exp-1206, in Google AI Studio and the Gemini API! I upgraded my llm-gemini plugin to support the new model and...

Genie 2: A large-scale foundation world model New research (so nothing we can play with) from Google DeepMind. Genie 2 is effectively a game engine driven entirely by generative AI - you can seed it with any image and it will turn that image into a 3D environment that you can then explore. It's remi...

Say hello to gemini-exp-1121 Google Gemini's Logan Kilpatrick on Twitter: Say hello to gemini-exp-1121! Our latest experimental gemini model, with: significant gains on coding performance stronger reasoning capabilities improved visual understanding Available on Google AI Studio and the Gemini API r...

When we started working on what became NotebookLM in the summer of 2022, we could fit about 1,500 words in the context window. Now we can fit up to 1.5 million words. (And using various other tricks, effectively fit 25 million words.) The emergence of long context models is, I believe, the single mo...

Preview: Gemini API Additional Terms of Service Google sent out an email last week linking to this preview of upcoming changes to the Gemini API terms. Key paragraph from that email: To maintain a safe and responsible environment for all users, we're enhancing our abuse monitoring practices for Goog...

llm-gemini 0.4 New release of my llm-gemini plugin, adding support for asynchronous models (see LLM 0.18), plus the new gemini-exp-1114 model (currently at the top of the Chatbot Arena) and a -o json_object 1 option to force JSON output. I also released llm-claude-3 0.9 which adds asynchronous suppo...

Anthropic declined to comment, but referred Bloomberg News to a five-hour podcast featuring Chief Executive Officer Dario Amodei that was released Monday. "People call them scaling laws. That's a misnomer," he said on the podcast. "They're not laws of the universe. They're empirical regularities. I ...

From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code Google's Project Zero security team used a system based around Gemini 1.5 Pro to find a previously unreported security vulnerability in SQLite (a stack buffer underflow), in time for it to be fixed pri...

Control your smart home devices with the Gemini mobile app on Android Google are adding smart home integration to their Gemini chatbot - so far on Android only. Have they considered the risk of prompt injection? It looks like they have, at least a bit: Important: Home controls are for convenience on...

Running prompts against images and PDFs with Google Gemini New TIL. I've been experimenting with the Google Gemini APIs for running prompts against images and PDFs (in preparation for finally adding multi-modal support to LLM) - here are my notes on how to send images or PDF files to their API using...

New in NotebookLM: Customizing your Audio Overviews The most requested feature for Google's NotebookLM "audio overviews" (aka automatically generated podcast conversations) has been the ability to provide direction to those artificial podcast hosts - setting their expertise level or asking them to f...

The other day I found myself needing to add up some numeric values that were scattered across twelve different emails. I didn't particularly feel like copying and pasting all of the numbers out one at a time, so I decided to try something different: could I record a screen capture while browsing aro...

Gemini API Additional Terms of Service I've been trying to figure out what Google's policy is on using data submitted to their Google Gemini LLM for further training. It turns out it's clearly spelled out in their terms of service, but it differs for the paid v.s. free tiers. The paid APIs do not tr...

Anthropic: Message Batches (beta) Anthropic now have a batch mode, allowing you to send prompts to Claude in batches which will be processed within 24 hours (though probably much faster than that) and come at a 50% price discount. This matches the batch models offered by OpenAI and by Google Gemini,...

Gemini 1.5 Flash-8B is now production ready Gemini 1.5 Flash-8B is "a smaller and faster variant of 1.5 Flash" - and is now released to production, at half the price of the 1.5 Flash model. It's really, really cheap: $0.0375 per 1 million input tokens on prompts <128K $0.15 per 1 million output toke...

NotebookLM now lets you listen to a conversation about your sources Google’s NotebookLM is effectively an end-user customizable RAG product. It lets you gather together multiple “sources” - documents, pasted text, links to web pages and YouTube videos - into a single interface where you can then use...

Updated production-ready Gemini models Two new models from Google Gemini today: gemini-1.5-pro-002 and gemini-1.5-flash-002. Their -latest aliases will update to these new models in "the next few days", and new -001 suffixes can be used to stick with the older models. The new models benchmark slight...

How streaming LLM APIs work New TIL. I used curl to explore the streaming APIs provided by OpenAI, Anthropic and Google Gemini and wrote up detailed notes on what I learned. Tags: apis, http, llms, json

Gemini Chat App Google released three new Gemini models today: improved versions of Gemini 1.5 Pro and Gemini 1.5 Flash plus a new model, Gemini 1.5 Flash-8B, which is significantly faster (and will presumably be cheaper) than the regular Flash model. The Flash-8B model is described in the Gemini 1....