Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mistral Patent for “Code implemented tool calls”

patentsgazette.uspto.gov

Post reply on HN
Print view View original

201–206 of 206 posts

Re: Mistral Patent for “Code implemented tool calls”

#201

Post by soraminazuki »

linuxhansl wrote: post #99

Having my name on a bunch of software patents - and, yes, I tried to get my name off them, but was not allowed - I can fairly confidently say: There is not A single worthy software patent out there. You know, one that is "not obvious to someone skilled in the art" and that actually protects a monetary investment. Software patent are a scourge of the software industry. Patents are designed to protect costly research;…

I'm skeptical of non-software patents as well. So much R&D are funded by taxpayer money yet private companies monopolize the profits. Patents are supposed to keep valuable knowledge public, yet that's not what happens because the primary motivation for patent applicants is to squash competition and they have an incentive to keep key information out. It seems all patents are doing is to make lives harder for the common people.

Re: Mistral Patent for “Code implemented tool calls”

#202

Post by freejazz »

jlokier wrote: post #199
freejazz wrote: post #189

Earlier quoted context omitted.

>Usually it's to defend against another company using a "blocking patent" by pursuing you for infringing their patent which is built upon the thing you patented, doing the next step which was always obvious to you. Would be pretty hard to sue someone for practicing a patent that cites that person in prior art who concurrently was inventing the same thing and would say how obvious it ones. You're going to tell me it's…

I've been in several patent lawyer meetings where we discussed blocking patent strategies and their mitigation when deciding what to patent, so I don't think it's made up. Company A publishes invention 1, when they know inventions 2, 3, 4 follow naturally in their own roadmap but those things aren't obvious to other people yet. Invention 1 is just a stepping stone in company A's larger vision, and it's not useful by…

You can't patent something that is already published - and, again, if you are already researching whatever step 2, that is great evidence to invalidate the step 2 patent made by another company. So, again, your scenario is highly specific, and also made up in that it is some hypothetical that exists in your mind and you are not pointing to any actual patents or examples of this happening that we could discuss with any specificity.

>Yes, but not all companies want to exclude. Some even want to share their work openly as they proceed. But even sharing openly and creating prior art as you go is not safe.

That's great, patents are publicly available documents. So patentees can feel free to share!

>For those companies, "what is the point of a patent if not to enforce the right of exclusivity it grants" -> the point is not to enforce exclusivity over anyone, because they don't want to. It's to use the granted rights as defensive leverage so they can continue developing, publishing and using their own work.

You're just making some semantic point for a reason I cannot understand. Patents only give the right of exclusion, what a patentee does with that right is up to them... They can trade on it, use it to bargain, give it up, whatever.

Re: Mistral Patent for “Code implemented tool calls”

#203

Post by HarHarVeryFunny »

For anyone, like me, who is/was confused by the patent diagram and labeling, the initial arrows labelled "tool call execution request" (client->server) and "tool calls" (server->LLM) seem to be confusingly labelled. This isn't a tool call being sent from client, via server, to LLM (which is not a thing - tool calls go in the opposite direction), but rather the user/agent's prompt, which as always includes tool "declarations", being sent from agent, via server, to the LLM.

The big picture here is that overall tool call flow works as normal, but rather than the LLM just generating tool calls, it is instead generating a "code block" that may include multiple tool calls/invocations. The server (between LLM and client) receives this code block and will execute it, but first has to execute any contained tool calls, some which it may do locally, and some via calls back to the client/agent as normal. Once all tools calls and the containing code block have been executed by the server (in a sandbox), then the final result is sent back to the client.

Re: Mistral Patent for “Code implemented tool calls”

#204

Post by lsaferite »

keeda wrote: post #197
ramoz wrote: post #193

Earlier quoted context omitted.

This is not a patent application. This is granted. They applied in March and was fast-tracked & issued in June. This is a full grant. You can see the claims here: https://ibb.co/k2mVVkFN

WTF! I just looked at the filing date of March 2026 and assumed this was still an application! I realize now that even for a patent application it had published too early, since they usually get published 18 months after filing. Turns out it was fast-tracked, which is why it was issued in ~2 months. It does claim priority to an earlier filing so the invention date is indeed March 2006. Not a single claim was question…

That's exactly what Anthropic was doing for a while.

https://www.anthropic.com/engineering/advanced-tool-use

Re: Mistral Patent for “Code implemented tool calls”

#205

Post by lsaferite »

thayne wrote: post #85
throw1234567891 wrote: post #84

I have prior art, there's a ton of prior art GitHub, good luck with that patent.

Plenty of things with prior art are successfully patentend. And are successfully enforced, because it is cheaper to pay the troll to cross the bridge than to take it to court. It isn't until the sue the wrong person who has the backbone and the resources to contest it that the patent gets revoked.

Not to mention, didn't it recently change to first-to-file as well?
Post reply on HN