conv.

All stories
Running 1d

Mistral Patent for "Code implemented tool calls"

Conversation activity · last 33 hours peak 4/hr

Peak 4 items in one hour at Aug 10, 9 AM; 20 items over 33 hours Aug 10, 9 AM — 4 itemsAug 10, 10 AM — 1 itemAug 10, 11 AM — 1 itemAug 10, 12 PM — 1 itemAug 10, 1 PM — 2 itemsAug 10, 2 PM — no itemsAug 10, 3 PM — no itemsAug 10, 4 PM — 1 itemAug 10, 5 PM — 1 itemAug 10, 6 PM — 4 itemsAug 10, 7 PM — 1 itemAug 10, 8 PM — no itemsAug 10, 9 PM — no itemsAug 10, 10 PM — no itemsAug 10, 11 PM — 1 itemAug 11, 12 AM — no itemsAug 11, 1 AM — 1 itemAug 11, 2 AM — no itemsAug 11, 3 AM — no itemsAug 11, 4 AM — no itemsAug 11, 5 AM — no itemsAug 11, 6 AM — no itemsAug 11, 7 AM — no itemsAug 11, 8 AM — no itemsAug 11, 9 AM — 1 itemAug 11, 10 AM — no itemsAug 11, 11 AM — no itemsAug 11, 12 PM — no itemsAug 11, 1 PM — no itemsAug 11, 2 PM — 1 itemAug 11, 3 PM — no itemsAug 11, 4 PM — no itemsAug 11, 5 PM — no items 4 items · 9 AM
Aug 11

Clustered from 20 items across 2 sources. Not yet parsed — the coverage below is the raw record.

Press coverage 1

Social posts 1

Voices from the web unedited

  • Regular PSA for patent-related discussions: what matters is the claims, so before commenting one should read those.Also this is a patent application, so it has not been examined yet. The claims at this point will always be over-broad, because that's just how patent prosecution works: the applicant (brazenly) tries to stake out as much…

    keedaHacker News23h agoview on Hacker News ↗
  • Oh wow :D Not commenting on the larger picture of why or why not Mistral might be doing that, but commenting on the idea itself: I plan to build my own harness soon, and one of its core tenants was, from the beginning, that it would parse every tool call the LLM attempts and executes them itself. I most cases, that would mean to delegate to one of…

    dev_dan_2Hacker News22h agoview on Hacker News ↗
  • 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)…

    HarHarVeryFunnyHacker News3h agoview on Hacker News ↗
  • 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…

    linuxhanslHacker News1d agoview on Hacker News ↗
  • Setting aside the tech, which looks like an asynchronous await across a network, the interesting question is why Mistral would patent this in the US.Simple, because the patent is less about protecting an invention than doing business in the US.The US is more hospitable to software patents than Europe. A US patent also gives Mistral something…

    mkovachHacker News1d agoview on Hacker News ↗
  • The Scala[1] community has been working[2] on something similar for a couple of years now, with papers already published[3]. I wonder if Mistral is not just trying to steal this work.[1]

    theboywhoHacker News1d agoview on Hacker News ↗
  • Software is mathematics. The idea you can patent software is as ridiculous as patenting a particular number or the technique of Riemann integration or whatever. I have my name on a couple of software patents[1] and everything about the process is bullshit. When I read my first patent I couldn’t quite believe that this is an accepted legal process…

    seanhunterHacker News16h agoview on Hacker News ↗
  • > Patents are designed to protect costly researchI'd argue that how they should have been, but the reality is quite the opposite. The patent framework is all about novel ideas rather than costly research, even though ideas aren't any valuable anymore - the easy stuff that is cheap to reproduce once the idea is known is already…

    tliltocatlHacker News1d agoview on Hacker News ↗
  • Some confusion in this thread... this is not a patent application. This is a fully granted patent. Looks like they fast-tracked it. Filed application in March, granted in June.You can see the actual claims here: https://ibb.co/k2mVVkFNYou can find the full patent on the USPTO search sitehttps://ppubs.uspto.gov/pubwebapp/search: "12670045".did

    ramozHacker News18h agoview on Hacker News ↗
  • 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…

    soraminazukiHacker News8h agoview on Hacker News ↗