Toolformer: Language Models Can Teach Themselves to Use Tools

Nothing, and there are methods which allow these types of models to learn to use special purpose tools of this kind[1]. [1] https://arxiv.org/abs/2302.04761 Toolformer: Language Models Can Teach Themselves to Use Tools

seanhunterNov 23, 2023View on HNParent context

It does. This is the plugins methodology described in the toolformers paper which I've linked elsewhere[1]. The model learns that for certain types of problems certain specific "tools" are the best way to solve the problem. The problem is of course it's simple to argue that the…

seanhunterNov 23, 2023View on HNParent context

Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761 Older one, but still very nice work.

manvel_hnJul 24, 2023View on HNParent context

That’s sort of what happens in the “toolformer” paper[1] which sets out the basic architecture by which things like chatGPT plugins work. Language models can learn to use “tools” provided by plugins. Those tools might themselves bee the specialized models you are describing…

seanhunterMay 24, 2023View on HNParent context

you just need to teach it to use a calculator https://arxiv.org/pdf/2302.04761.pdf

kz919May 20, 2023View on HNParent context

It should be in line with the likes of this - https://arxiv.org/abs/2302.04761 or https://twitter.com/minosvasilias/status/1627076214639976449 I didn't say guardrail to mean anything particularly elaborate. The pre-prompt for Bing has instructions to avoid adversarial arguments.

famouswafflesMay 13, 2023View on HNParent context

This document seems to have been written before the toolformer paper[0], which fine tunes the model to use tools (e.g search) to retrieve information. [0]: https://arxiv.org/abs/2302.04761

johntb86Apr 27, 2023View on HNParent context

The recent post from Stephen Wolfram[1] is pretty good as an introduction, but I haven't seen any super comprehensive material that tries do dissect all the interesting behaviour we see in the really big llms. For that just reading the relevant papers themselves has been pretty…

Version467Apr 3, 2023View on HNParent context

> LLMs can't to my knowledge process a request into a lookup on say an actual database of facts at the moment or parse a request into API actions. They can: https://arxiv.org/abs/2302.04761 > In this paper, we show that LMs can teach themselves to use external tools

pornelMar 28, 2023View on HNParent context

I am actually not quite sure what would be best to recommend, as the pandemic has seen me lag behind the zeitgeist somewhat. A recent favourite would be the Toolformer paper [1], that I intend to read in detail later today. If an LLM would be able to use external tools…

ninjinMar 28, 2023View on HNParent context

I think I've read it's based off Toolformer (https://arxiv.org/pdf/2302.04761.pdf)

jeadieMar 26, 2023View on HNParent context

They already can: https://arxiv.org/abs/2302.04761 (Toolformer) There's even a zero-shot version based on prompt engineering: https://toolformerzero.com/.

grafs50Mar 19, 2023View on HNParent context

Since the GPT-4 paper didn't reveal any details of their model, it's possible that GPT-4 is already using some variant of toolformer (https://arxiv.org/abs/2302.04761).

goldwelder42Mar 17, 2023View on HNParent context

Bing chat already hooks into a web search tool. It shows "Searching for: ..." when it does that. This is kind of the point of Bing chat. edit: a paper about how to hook up LLMs to any external tool https://arxiv.org/abs/2302.04761

wcoenenMar 17, 2023View on HNParent context

He likely meant techniques such as ToolFormer[1] where the language model will output a "request" (in some text syntax) that another system can parse, run and report back. [1] https://arxiv.org/abs/2302.04761

sprobertsonMar 14, 2023View on HNParent context

That's called Toolformer (Facebook AI Research): https://arxiv.org/abs/2302.04761 Toolformer: Language Models Can Teach Themselves to Use Tools

jkbycMar 9, 2023View on HNParent context

Here you go, here's a bunch of papers that you have not read. If you had read them then you would know that the errors are predictable and therefore there are many measurable ways to make improvements. Toolformer: Language Models Can Teach Themselves to Use Tools…

williamcottonMar 2, 2023View on HNParent context

Hooking ChatGPT (and similar architectures) into applications is going to be the next big thing. It just takes time to hook up various systems. Eventually a vision module will be integrated and it will probably be able to "figure out" most systems. There's a lot of money to be…

jackblemmingMar 1, 2023View on HNParent context

Here’s some recent ML work from Meta that I really like: Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761

williamcottonFeb 28, 2023View on HNParent context

You can make small LLMs more performant than large ones like GPT-3 by fine-tuning on specific tasks or providing them tools to offload precise calculations: e.g. Toolformer: https://arxiv.org/abs/2302.04761 which uses APIs and functions to improve GPT-J beyond GPT-3 for various…

imranqFeb 24, 2023View on HNParent context

There's research being done on this: https://arxiv.org/abs/2302.04761 At its core using an LM alone to solve factual problems seems silly: It's not unlike asking Dall-E to draw DOT compliant road signs. I've gone at length at how unfortunate it would be if LMs start to get a bad…

BoorishBearsFeb 23, 2023View on HNParent context

Fine-tuning on smaller models like GPT-J (also trained on The Pile) worked well for Toolformer: https://arxiv.org/abs/2302.04761

williamcottonFeb 23, 2023View on HNParent context

One recent paper to be added to this list of Approaches/Techniques is: Toolformer: Language Models Can Teach Themselves to Use Tools https://arxiv.org/abs/2302.04761 The authors show a valuable method of using prompts to generate training data to be used for fine-tuning. Check…

williamcottonFeb 21, 2023View on HNParent context

Using the terminology that I'm working with this is an example of a second-order analytic augmentation! Here's another approach of second-order analytic augmentation, PAL: https://reasonwithpal.com Third-order, Toolformer: https://arxiv.org/abs/2302.04761 Third-order, Bing…

williamcottonFeb 21, 2023View on HNParent context

They literally "do context", as they do in-context learning. Also, factuality can effectively be solved by chain-of-thought prompting[0] and the use of external tools[1], also see toolformerzero[2] for a simple example. [0]: https://arxiv.org/abs/2201.11903 [1]…

danielblnFeb 21, 2023View on HNParent context

In their current iteration the models are very neutered. It’s been demonstrated that GPT models are fairly good at choosing when to perform a task. Obviously lots of APIs and machinery is needed to actually perform tasks, but the heavy lifting “intelligence” portion can be…

valineFeb 18, 2023View on HNParent context

I love the mental model of GPT as only one part of the brain, but I believe that the integration of other "parts" of the brain will come sooner than you think. See, for instance, https://twitter.com/mathemagic1an/status/1624870248221663232 / https://arxiv.org/abs/2302.04761…

btownFeb 13, 2023View on HNParent context

Except it’s already been shown LLMs can do exactly that. You can prime the model to insert something like ${API CALL HERE} into its output. Then it’s just a matter of finding that string and calling the api. Toolformer does something really neat where they make the API call…

valineFeb 13, 2023View on HNParent context

Relevant to this discussion is the Toolformer paper that was just released today from Meta AI. To me the exciting result from the paper is that it appears that much smaller models can be used to translate human intent into actions: https://arxiv.org/abs/2302.04761

localhostFeb 10, 2023View on HNParent context