SkipWatch launch film (remake)
A remake of a Claude Code plugin's launch film: a dithered kung fu figure performs the skill.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
A video player cycles through sample subjects before landing on a kung fu course. A speed menu offers ‘skip watching’ and the player advances to the end.
- 0:06
A Claude Code prompt runs /skipwatch with a video link. The film presents a 48-minute video becoming a skill in one command; the kung fu timeline is labelled ‘Illustrative run.’
- 0:12
A white dithered figure bows, takes a horse stance, punches, then blocks and counters. Some steps carry source-time tags. A quoted example and a SKILL.md panel show how the steps become a reusable skill.
- 0:30
A prompt invokes Skill(kung-fu-basics). The figure responds to another with the displayed answer: ‘Block. Step in. Counter.’
- 0:36
The SkipWatch mark appears as examples cycle through kung fu, sourdough, TypeScript, linear algebra, cinematography and quantum physics. The screen labels these illustrative examples.
- 0:44
The closing card shows installation and usage commands, github.com/robert-botto/skipwatch, and ‘Free and open source (MIT).’
Guardcell launch film
The launch film for Guardcell, my open-source Outlook add-in: real email incidents, then the question it asks before Send.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
An Outlook Send button gives way to headlines about real email disclosures. The film identifies the quoted voices as synthetic.
- 0:23
Emails rebuilt with invented names show a party invitation with 2,743 people's details attached, a clinic newsletter exposing 781 addresses, 245 applicants visible to one another, bank accounts sent outside, payroll sent to a scammer, and a password sent to an impostor.
- 0:58
The password email is shown again with Guardcell. On Send, a dialog identifies the password and offers Send anyway, Review or Don't send. The review pane highlights the issue; the sender removes the sentence and sends again.
- 1:10
The film illustrates checks of recipients, message text and attachments with examples including passwords, card numbers, lists, margins and client remarks. A laptop diagram says the checks run without a server.
- 1:29
A grid of rebuilt emails accompanies the film's result: Guardcell asks about 35 of 43 documented incidents that went outside. The case study explains that these replays informed development, rather than proving historical incidents would have been prevented.
- 1:37
An administrator uploads a manifest and assigns users. The closing card calls Guardcell free and open source under Apache 2.0 and points to its GitHub repository.
Decision Models launch film
A one-minute launch film for a platform serving open decision models.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
A green line travels across a paper-like scene as Decision Models is introduced as inference for open-weights decision models. Cards representing new models accumulate around the question: ‘Which one do you build on?’
- 0:12
A JevBench scoreboard credits founder Florian Standhartinger and highlights the open-weights models among the leading entries. The film presents five models through one Jev-compatible API, with separate service terms.
- 0:24
An illustrative support request asks to update an invoice address. A decision model selects billing with a displayed 0.87 score; the film says the probabilities are illustrative, not measured API results.
- 0:32
A dated, company-measured comparison shows 5.28 versus 31.73 decisions per second for Perplexity Decider v1.1, using several questions per request on the same RTX PRO 6000 GPU. The film also notes a smaller gain for single-question requests and that some answers differ.
- 0:38
An illustrative cost counter reaches $6.67 for one million S1-FAST decisions on the peer-to-peer tier, using 351 input tokens per decision, output free and excluding tax. The film compares that 2026 list-price example with Jev.
- 0:44
The film points to public REAX Engine code, then shows a globe and an invitation to become a hosting provider, with hardware and registration requirements. It closes with the Decision Models mark and the line ‘Served by the people, for the people.’
REAX: served by the people
Decentralised inference in one picture: requests answered by GPUs that independent people run.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
A compact grid of points spreads into a network as ‘One data center’ changes to ‘Served by the people.’ The heading identifies REAX Network and Bittensor subnet 92.
- 0:05
An illustrative decision card asks whether to escalate a ticket. A line travels through the network to a GPU run by an independent miner; the example displays 0.91 for escalate and 0.09 for keep.
- 0:10
A validator appears. The film says miners are checked on fresh questions and notes that network processing is opt-in on the peer-to-peer tier, company GPUs provide fallback, and answers are checked on a sampled basis.
- 0:16
The REAX mark closes the film with ‘AI by the people, for the people’ and decisionmodels.io.
REAX: can your 9B model take #1?
A recruitment film for open model competitions.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
REAX Competitions asks whether a 9B model can take first place. A public development risk-assessment item shows likelihood 3 and impact 4. Because a test is overdue, the effectiveness rating is void; the displayed score of 12 exceeds the limit of 8. Ranked items are described as sealed.
- 0:08
Illustrative routing examples send a duplicate-invoices SQL task to a mid-size language model and a higher-stakes legal question to a large one. The film names demand forecasting and risk assessment as tracks and invites openly licensed models of up to 9B parameters.
- 0:16
Two sealed draws represent scoring on unseen questions: the first has 300 fresh items, and the second follows 12 hours later. The 2026 closing card shows reax.co/competitions and an October 30, 12:00 UTC deadline.
REAX Engine
Same GPU, same model, faster: one engine result, shown as simply as possible.
Read a visual description +
A description of the picture and on-screen text, with approximate times. Product details and offers are shown as they appeared in the 2026 films.
- 0:00
An animated comparison introduces ‘Same GPU. 6× the decisions.’ For Perplexity Decider v1.1, the bars show 5.3 decisions per second for the BF16 reference server and 31.7 for REAX Engine using FP8 and shared state.
- 0:10
The film attributes this result to company-measured Decision Index requests in October 2026 on the same RTX PRO 6000 Blackwell GPU. It separately reports 3.1× on single-question requests, says the score is within noise, and notes that about 2% of answers change.
- 0:14
The closing card points to github.com/reaxlabs/reax-engine and describes a miner competition as coming soon at the time of the film.
