Strava Conversational Tools
Reading Time: < 1 minute
The sun is shining. For a day or two the grey Autumn weather is gone. This would be a good time for a spontaneous bike ride. The issue with this is that Strava is great for sharing activities that are planned in advance, and those that have passed. It's easy to get kudoes. It isn't easy to converse.
They have instant messaging but it is only available via the mobile phone app, rather than from the web interface. It is seldom used so to use it might appear spammy to use it like we use Signal or Whatsapp.
With the beautiful weather, and blue skies we have today, it seems a shame not to have a spontaneous social ride. It would be easy to say "hey, let's meet here at that time and go for a spontaneous ride. This is especially true since the weather could be bad for the weekend. It might rain for the entirety of Saturday and Sunday.
I suspect that weather, rather than motivation, is keeping people indoors. If the weather was nice people would leave their indoor trainers and enjoy the Autumn air, sights and sounds.
And Finally
I suspect that if Strava, and Meetup.com, as well as WhatsApp for events, became more conversational, so the amount of noise would go up, as well as the number of activities decline. Strava, and Meetup.com fill the niche of giving us a place to organise events, and then speak in person.
Twitter was great for online conversations that eventually resulted in tweetups, but those days are long gone, due to algorithms, and now AI bots making conversations between individuals more challenging.
#conversational #coonversations #networking #social #spontaneous #strava
![👾According to the readme file, "Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of RAM." [HarryR]'s goal is to see how small an AI project can go, while still having a "personality". Can the AI be trained and fine-tuned? It seems that [HarryR] has done it in just 40KB, including inference, weights, and chat style user interface.👾
⁉️[HarryR] has kindly detailed the features of this Z80 AI project⁉️
• Trigram hash encoding: Input text is hashed into 128 buckets - typo-tolerant, word-order invariant
• 2-bit weight quantization: Each weight is {-2, -1, 0, +1}, packed 4 per byte
• 16-bit integer inference: All math uses Z80-native 16-bit signed arithmetic
• ~40KB .COM file: Fits in CP/M's Transient Program Area [TPA]
• Autoregressive generation: Outputs text character-by-character
• No floating point: Everything is integer math with fixed-point scaling
• Interactive chat mode: Just run CHAT with no arguments](https://files.mastodon.social/cache/media_attachments/files/116/148/326/283/992/135/original/dad7e974fe652505.jpeg)
![[ImageSource: HarryR]
👾The project comes with two examples. Tinychat is a conversational chatbot that responds to greetings and questions about itself with very short replies. The other is Guess, a 20-question game where the model knows a secret and I must try to guess.👾
Both of these examples are made available as binaries for use with CP/M systems and the Sinclair ZX Spectrum. The CP/M files are typical .COM files that anyone can easily run. For the ZX Spectrum, there are two .TAP files, cassette tape images that can be loaded into an emulator, or on real hardware.
The chatbot's AI is limited but nuanced.
• OK - acknowledged, neutral
• WHY? - questioning your premise
• R U? - casting existential doubt
• MAYBE - genuine uncertainty
• AM I? - reflecting the question back
⁉️According to [HarryR], "....it's a different mode of interaction. The terse responses force you to infer meaning from context or ask probing direct yes/no questions to see if it understands or not". The responses are short on purpose, sometimes vague, but there is a personality inferred in the response. Or could this just be a human brain trying to anthropomorphize an AI into a real person?⁉️](https://files.mastodon.social/cache/media_attachments/files/116/148/326/316/860/680/original/100ed8b175f03a5d.jpeg)
![[ImageSource: Gettyimages]
⁉️Will AI Create The Z80-pocalypse⁉️
The short answer is no, there is nothing to fear! But the Z80 has seen its life threatened during its 50-year lifespan.
👾In 2024, the Z80 finally reached end of life/last time buy status according to a Product Change Notification [PCN] that I saw via Mouser. Dated April 15, 2024, Zilog advised customers that its "Wafer Foundry Manufacturer will be discontinuing support for the Z80 product.…" But fear not, as back in May 2024, one developer was working on a drop-in replacement. Looking at Rejunity's Z80-Open-Silicon repository, I can see that did in fact happen via the Tiny Tapeout project.👾
<https://www.mouser.com/PCN/Littelfuse_PCN_Z84C00.pdf>
<https://github.com/rejunity/z80-open-silicon?tab=readme-ov-file>](https://files.mastodon.social/cache/media_attachments/files/116/148/326/341/328/751/original/6b63c8d09de86796.jpeg)
