I actually really like that inverse Kickstarter idea, makes a lot of sense especially if you did some kind of enter some pain/problem, search through existing idea markets and you can throw money towards ideas that would solve whatever pain point you have. Builders would essentially just have a market of validated ideas and could submit a ‘bid’ before a set deadline and the finders would vote on which is best then the funds would resolve to whatever builder made the best product.
It’s a really interesting project, worth checking out the video where he merged it with a companion computer to do computer vision tasks and inject controls straight into the flight controller https://m.youtube.com/watch?v=uaY2G5Kbj_g
True, certainly something you could do with Tailscale+tmux but if this makes that a lot easier then it could end up being popular, increasingly the people who are pushing the most money into the likes of Anthropic are not rhe people focusing too much on the amount of money being put towards achieving their goal, rather the progress(tbh more realistic to say perceived progress) towards that goal in the shortest amount of time.
Fair enough but the examples shown could surely just display some pre-cooked examples to give a demo of how rhe product works with no real cost to you or barrier to potential users.
Confused me at first as when I saw mention of local + the single file thing in the GitHub I assumed they were going to have llamafile bundled and went looking through to see what model they were using by default.
100%, trying a bit of an experiment like this(similar in that I mostly just care about playing around with different agents, techniques etc.) it has built out literally hundreds of tests. Dozens of which were almost pointless as it decided to mock apis. When the number of failed tests exceeded 40 it just started disabling tests.
And most of the big players now have some kind of browser or bowser agent that they could just leverage to gather training data from locked down sources.
^This 100%. Junior SWE here. Agentic coding has kinda felt like a promotion for me. I code less by hand and spend more time on the actual engineering side of things. There’s hype in both directions though. I don’t AI is replacing me anytime soon(fingers crossed), but it’s already way more useful than the skeptics give it credit for. Like most things the truth’s somewhere in the middle.
In terms of training your own models, is there enough COBOL available for training or are you going to have to convince your customers to let you train on their data (do you think banks would push back against that?)
Actually seems like a really cool product, not sure if it would be that useful for any serious reading due to the small size but probably useful for displaying a calendar and other widgets.
“ These endpoints are focused on higher tool-calling accuracy by routing requests to providers that demonstrate measurably better tool calling performance.
Exacto endpoints are available for:
- Kimi K2
- DeepSeek v3.1 Terminus
- GLM 4.6
- GPT‑OSS 120B
- Qwen3 Coder ”
Agreed, “ Popularity as a better indicator”. Hypothetically you could look at popularity over time to filter out viral rot content and work out if people feel the content is useful.