479 karma · joined January 4, 2022
I think this is such a great reframing. It makes so much sense; I need an AI that acts more as a HUD and gives me superpowers, not just a copilot that can tell me when I've misspelled a word.
Not a huge deal since it's still cents per session, but my bigger issue was the weird change in tone. It became a lot more pretentious and over-explanatory.
Heavy prompt reworking helped but maybe that's just the cost of being better at coding and ARC-AGI?
Obviously a CTO is not going to walk away from the technology just because it's not good enough. That much more incentive for someone to create a powerful enough harness that can direct that power safely and productively. Like a nuclear core, we'll need to come up with the graphite rods and water tank. And if tokens are essentially free, why not, for every million tokens, spend 10x tokens on code review, testing, etc?
- Deepseek V4 Flash is impressively capable. Sonnet still beats it out by a thin margin, but the real kicker is that a typical session with Sonnet at current API costs is ~$2. The same session with Deepseek is 2 cents (ha). Its even allowed me to consider offering free-with-limits API usage on my own app. - Taalas (or competitors) have a lot going for them. If anything I feel like they need to join hands with these smaller model makers and converge in 2028
Maybe I'm thinking too far ahead but I'm hoping maybe I can cover the (future?) compute costs by charging for the heavy duty ML that would have to be run non-locally but IDK. This isn't critical yet but would love to hear your musings.
Great work! I hope to see more and more apps like this in the spirit of "Toss it all into context"
Popular microscopy models like Cellpose[0] have leaned heavily on the cornucopia of open and SOTA power. I have no doubt thousands of biologists have benefitted from the capabilities these models bring. I think it was unthinkable just 5 years ago that a single biologist with just a laptop could do mass-segmentation at this kind of fidelity.
Then there's Napari and it's plugin ecosystem[1] that wouldn't exist without the Chan Zuckerberg Initiative. Again, I'm not trying to glaze them but as someone in the biotech/microscopy space I can't understate how often I use and benefit from their open source.
[0] https://cellpose.readthedocs.io/en/latest/models.html [1] https://chanzuckerberg.com/rfa/napari-plugin-grants/
These cool demos come up now and again and it always takes me a minute to remember I have reduced motion. But for that minute I was disappointedly clicking around thinking "Whats the big deal?"
It's crazy to me that we are still discovering these microscopic yet crucial parts of nature around us.
I guess I'm agreeing with your point that its hard to pre-emptively define what "bad UI" is when it's often so close to "efficient UX", so just go downstream.
Armin Ronacher's "Absurd Workflows: Durable Execution With Just Postgres" https://lucumr.pocoo.org/2025/11/3/absurd-workflows/
What's "alignment" in your context. In bioimaging it usually refers to aligning something to a reference atlas (like the Allen Reference Mouse Brain Atlas) or aligning two microscope channels (like the red channel and green channel)
> This reminds me of Antirez's "Don't fall into the anti-AI hype". In a sentence: These foundation models are really good at optimizing these extremely high level, extremely well defined problem spaces (ie multiply matrices faster). In Antirez's case, it's "make Redis faster".
``` In a single index.html, no dependencies, sparse styling, create an app that <idea> ```
Even before AI, it's how I built small tools, and there's something lovely about being able to email my friends the tool, and tell them "If you want to make a change, toss it to your LLM!"