[HN Gopher] Mistral Agents
       ___________________________________________________________________
        
       Mistral Agents
        
       Author : eitanturok
       Score  : 144 points
       Date   : 2024-08-07 19:32 UTC (3 hours ago)
        
 (HTM) web link (mistral.ai)
 (TXT) w3m dump (mistral.ai)
        
       | Oras wrote:
       | Genuine question, are there any examples of agents in production?
        
         | simonw wrote:
         | Depends what you mean by "agents".
        
           | Oras wrote:
           | The article is about LLM agents, so I'm asking in context.
           | 
           | To clarify more, I see frameworks like CrewAI and similar,
           | with tools even from Microsoft to define these "agents"
           | quickly. But when I tried them, I noticed they are no more
           | than chain of thought CoT functions to ask/extract/generate
           | based on user input and functions output.
           | 
           | As such, they can be quite unpredictable, hence my question
           | of examples of LLM agents being used in production. I just
           | don't see their value, but I might be missing something so
           | wanted to see examples to understand more.
        
         | colkassad wrote:
         | Depends on your definition. I created a mapping application
         | that allows one to navigate and style the map with natural
         | language (more or less) as well as some prototype database
         | interaction. When the user inputs a prompt, it gets sent to an
         | "agent" whose sole purpose is to send a request to the API with
         | a custom system prompt with few-shot examples stating something
         | along the lines of "determine which agent should handle this
         | request...only respond with one of [NavigationAgent,
         | StyleAgent, ...]". When the response comes back, the prompt is
         | then sent to the proper agent to handle the request. Each agent
         | has function definitions for properly returning parameters to
         | use to manipulate the map. I don't use any special libraries
         | like langchain or anything, it's just regular API calls
         | organized into classes that have specific system prompt
         | behavior defined, function definitions, and some user prompt
         | context ingestion when required (e.g. the current extent of the
         | map).
        
           | Oras wrote:
           | Why can't this be done with functions? I don't see why you
           | need the complexity and unpredictability of using "agents" to
           | do that.
           | 
           | I might be missing something?
        
             | colkassad wrote:
             | I call them agents just because. I'm just doing function
             | calling with custom system prompts for the most part. It's
             | hardly complex, I wrote most of it in a few days.
             | 
             | EDIT: I should add that the first step is used to cut down
             | on the number of function definitions I need to send to the
             | model on each user prompt. Navigating a map can be done
             | with as few as four function definitions but styling a map
             | gets out of control fast (google "Mapbox Style
             | Specification" if you want to see why).
        
         | dudus wrote:
         | Doctors are already using agents for scheduling. These agents
         | can access calendar and talk to patients to arrange scheduling,
         | changes, conflicts etc
        
           | pton_xd wrote:
           | This use-case actually makes a ton of sense. How many other
           | low-hanging fruit applications for agents are out there like
           | that?
           | 
           | Although now that I think about it, a lot of doctors
           | practices have a MyChart-style portal where you can schedule
           | an appointment yourself. Why does an LLM need to be involved
           | in that process? I guess for people who still want to
           | schedule over the phone, the LLM agent makes sense. Kind of,
           | assuming you don't have any special case problems. Which
           | patients most likely do, if they're calling in. Is an LLM
           | actually a good solution here?
        
         | Areibman wrote:
         | Yes, here's a directory of many of them https://staf.ai
        
         | dsissitka wrote:
         | Not quite sure if this is what you're looking for but Amazon
         | has hidden their description/review search box behind a "Ask
         | Rufus about this product" box. For example, go here and Ctrl+F
         | for "Looking for specific info?":
         | 
         | https://www.amazon.com/PolyScience-Temperature-Controlled-Co...
        
       | qeternity wrote:
       | Since we've apparently moved from calling everything a Copilot to
       | calling everything an Agent, this seems much closer to OAI's GPT
       | Store than anything that is truly agentic.
        
         | voiper1 wrote:
         | but worse! there's no tools or RAG/data yet...
        
           | htrp wrote:
           | don't forget about agentic workflows
        
           | jsemrau wrote:
           | No memory, no reasoning, no planning.
        
             | rvnx wrote:
             | We just have to wait that LLaMA does it, then suddenly they
             | will have it.
             | 
             | Mistral is like FitGirl Repacks for LLaMA.
        
         | reducesuffering wrote:
         | Because Copilot implies a human working in tandem with AI. An
         | agent is an autonomous process. The goal of agents is to remove
         | any human agency from the process. Need software done? It won't
         | be a human's job. It will be the agent's in an iterative loop.
        
           | qeternity wrote:
           | I understand why. Most products claiming to be agents today
           | are simply prompts.
        
         | baxtr wrote:
         | Finally, finally we have a true and worthy successor to "AI" as
         | buzzword. It's "Agents" ladies and gentlemen.
         | 
         | Make sure to put it into your pitch as often as possible.
        
           | 8338550bff96 wrote:
           | Computers, desktops, and now we have these things called
           | "Virtual Machines".
           | 
           | Meaningless buzzword central.
           | 
           | <<eats gallery peanuts>>
        
           | xnx wrote:
           | Agent Intelligence or "AI"
        
             | flessner wrote:
             | Doesn't "AI" already stand for Apple Intelligence, so that
             | might be a bit confusing...
        
               | xnx wrote:
               | Anything Intelligence
        
       | voiper1 wrote:
       | >Agents help you create custom behaviour and workflows with a
       | simple set of instructions and examples. So, it's just custom
       | instructions baked in? I hope at least it's harder for them to
       | get overwritten by the user?
       | 
       | >We're working on connecting Agents to tools and data sources...
       | So tools and RAG for data sources aren't available yet.
       | 
       | Way behind GPTs/assistants. What's the point of this yet?
        
         | eitally wrote:
         | To me, this looks like a direct competitor to AI21 Labs:
         | https://www.ai21.com/
        
           | toomuchtodo wrote:
           | OpenAI is supposedly working on agents as well:
           | https://news.ycombinator.com/item?id=41125900 (subthread)
        
       | geepytee wrote:
       | This is basically Mistral's attempt at custom GPTs?
        
       | rodoxcasta wrote:
       | Wait, this 'Agents' thing seems to be just a way to couple a
       | system prompt and temperature to a model, that's it?
       | 
       | What's the difference from sending the system prompt in the api
       | call, as usual?
       | 
       | Edit: Oh, missed that: "We're working on connecting Agents to
       | tools and data sources."
        
         | refulgentis wrote:
         | There's this massive gap between those who can call API and
         | those who can't. If you can't, then you get the same
         | aspirational-AGI chat UI as everyone else.
         | 
         | I agree with the implied statement that 'Agents' doesn't feel
         | right. Reminds me more of the projects that put the model in a
         | loop.
         | 
         | It does feel to me to be a really tough thing to name & market,
         | I'm about to release an app for this across all providers, I
         | call it "Scripts" with "Steps" like chat, search, retrieval,
         | art...
        
           | DebtDeflation wrote:
           | I implemented a number of enterprise Conversational AI tools
           | for customer service back before the GenAI craze started and
           | we used to just call it service orchestration and
           | data/application integration. The chatbot was used to figure
           | out what the customer wanted to do and then from there it was
           | just about automating some business workflow. Customer wants
           | to pay their bill, the bot needs to pull their current
           | balance, get their payment information, process the payment.
           | Customer wants to return a product, the bot needs to retrieve
           | the order info, initiate an RMA, process a refund, etc. These
           | were all well established business process that the bot would
           | execute by making API calls or kicking off an RPA routine.
           | The "agent" talk sounds to me like "let the LLM figure out
           | what it needs to do and then do it" which I'm not even sure
           | is the right approach for most enterprise use cases, it's how
           | you get people tricking chatbots into selling them a new car
           | for $1.
        
         | TechDebtDevin wrote:
         | Why is tool picking such a hard functionality for these vendors
         | to implement.
         | 
         | Seems like a lot of the heavy lifting will come from 3rd
         | parties making their APIs compatible with llms.
         | 
         | There should be some sort of extension type app where people
         | can build extensions or "tools" for llms and share them (I
         | guess openAI sort or attempts to do this). Say I want to build
         | one for Toast to order food. I can collect the info needed to
         | run that tool (toast account info or whatever) and an API key
         | for an appropriate llm and then use this configuration info for
         | Toast to build out a middleware that can use natural langauge
         | to build out an order and send the request to Toast via some
         | function call.
         | 
         | This seems very doable and I don't understand why there aren't
         | a million of these "tools" already built into some LLM centric
         | tool aggregator/ web store. What is the hold up? Is it just 3rd
         | parties not wanting to hand out API access for things that
         | require payment to applications controlled by llms? Would these
         | 3rd parties rather have their own assistant tool they run? I'd
         | imagine that some central llm-extension aggregator could have a
         | central mechanism for payment methods that the llm had access
         | to that could be used to implement safegaurds.
         | 
         | Or is it simply that any assistant type tool that could be
         | easily generalized like ordering food, booking a flight or
         | inputing calender events is simply easier to handle doing
         | yourself than asking an llm to do for you?
        
       | simonw wrote:
       | I've been complaining about how vague and loosely defined the
       | term "agents" is like a broken record for months. This is not
       | going to help.
        
         | finikytou wrote:
         | it is quite simple to explain. it is a while(1) and some if.
        
           | simonw wrote:
           | The problem is that if you ask two people you're likely to
           | get two different answers. And those people probably
           | incorrectly think that their version of a definition for
           | "agents" is the same as everybody else's.
        
           | TeMPOraL wrote:
           | Yeah, but there is still no while(1) here.
        
       | pradn wrote:
       | One sad part of the GenAI wave happening right now is that we're
       | past the golden age of open APIs.
       | 
       | It's hard to read data with widespread anti-abuse checks
       | (CAPTCHAs), lack of open-format data (RSS support being spotty),
       | and restricted APIs (ex: Twitter API). Companies have all the
       | incentives to prevent bot use, and select for human eyeballs.
       | 
       | If we had a Yahoo Pipes sort of golden age, GenAI agents would
       | have a vaster playground to play in, and would be more useful for
       | us.
       | 
       | Consider building an agent for choosing what to do on weekends
       | for a group of friends. The agent would need to keep state for
       | past activities (X, Y, and Z went upstate to Storm King last
       | week) and users' preferences (ex: liking dosas or Calder, dietary
       | restrictions). This part is easy enough - you could just keep a
       | notebook that's passed as context. Older context gets simply
       | deleted or condensed into high level points.
       | 
       | But would it be easy for the agent to:
       | 
       | 1) Look up nearby restaurants and events? (Perhaps Resy/OpenTable
       | allow listing restaurants, but it's likely they have tons of
       | anti-abuse tech. Is there even a place where you could see a list
       | of public events - Google pays a third-party for this feed.)
       | 
       | 2) Actuate on behalf of the user? (Do Resy and OpenTable allow
       | authority delegation so the agent could book restaurants for
       | users? There's no standard way to do this across venue types -
       | concerts, museums, cooking classes. Is it realistic for agents to
       | click through these sites on their own?)
        
         | exe34 wrote:
         | seems to be a monetisation problem. everybody wants their cut.
         | so any super agent needs to figure out how to pay them.
         | 
         | we could imagine a data/api marketplace, where such an agent
         | could pay for the data and subscriptions.
        
           | tanelpoder wrote:
           | This could/should be a direction for companies like Zapier...
           | 
           | Edit: or Stripe.
        
       | ilaksh wrote:
       | The SOTA models have excellent instruction following capability
       | and the ability to output in any format you want including JSON.
       | 
       | That's all you need from the model to be able to use it in an
       | agent. Tell it to output commands in a given JSON format.
       | 
       | I assume that Mistral's API already allowed you to define the
       | system prompt, right?
        
       ___________________________________________________________________
       (page generated 2024-08-07 23:01 UTC)