modo_

I've seen people set up crons to run every 15 minutes and accidentally spend a ton because the agent runs every time, even when there's nothing to do. Do you have a way to run a cheap check first and only wake the agent when something actually needs its attention?

I think there are a lot of people using AI who aren't as familiar with these tools as us. We stop noticing a lot of the complexity when we pick it up gradually. There are so many powerful capabilities built into codex/ claude code that have little or no UI affordance.

it's tons of small things like choosing the right effort level for a task. or knowing when to ask for subagents. oh, you can have two threads working at the same time and communicating with each other? you can do /side to parallel path and fold that back into the main thread?

which of these things happens automatically, and which do you need to ask for? and does any of this still work the way it did a few months ago?

the list goes on forever. many users of AI are only just now getting comfortable with skills (and probably still writing bad skills unfortunately hah).

A lot of the specific things you learned may have become obsolete. But there's still a gap between what these tools can do and what most people know how to get them to do. Keeping up with that is a skill too, but perhaps not forever.

Would love an option for the steepest route! I run a lot in SF and try to maximize vertical gain on my routes

Here's a certified human written post from the one and only Yvon Chouinard about tumplines. Patagonia actually used to sell a tumpline compatible with some of their packs briefly in the 2010s!

https://www.patagonia.com/stories/culture/design/on-tumpline...

I've been a trackpad proponent for years, but with Steermouse I've been able to dial in my MX Master so perfectly that I find myself missing it when I travel.

What really took it to the next level for me were adding chord mappings. For example I can hold right mouse button + scroll the thumb wheel to adjust volume. So convenient!

Your point on the harness is interesting. How do you distinguish characteristics of the model from characteristics of the harness?

In the early days I feel it was more apparent. You would frequently see the model making failed tool calls etc.. but now that feels so rare. I'm not confident I can perceive whatever shortcomings of the harness remain.

I was using Context back when it was still Brand.dev. I found it to be a great product- one of those rare APIs that immediately made a problem I had disappear. Had it in production within an hour of signing up

Agents need clean/current context from the web, and this is the best way I’ve found to give it to them. The internet is clearly moving in this direction: companies are starting to realize their sites need to be legible to agents. Some are already adapting but many haven’t yet. Context feels like an important part of that transition

Yahia is a great builder. His pace of expansion has been impressive, excited to see where he takes Context.

Exactly right. Climbers care a lot about the ethics of an ascent. It’s interesting how much those ethics have changed over the history of the sport.

One of the core ideas is that later climbers should respect or improve upon the style of the first ascensionist. e.g. if a climb was first done using siege tactics, then doing it in a single day is celebrated. But making a climb easier or safer after the fact is much more controversial, because it can feel like changing the nature of the route itself.

Snake Dike is a good example that’s flared up recently in the climbing world. It’s a classic, relatively easy route up Half Dome, and many climbers free solo it. But because it’s a face climb, protection mostly comes from bolts drilled into the rock. The first ascensionist placed very few bolts, which left long runouts and real consequences if you fall.

To many old school climbers, adding bolts to Snake Dike is disrespectful because the risk is part of the route’s character. Their view is basically: don’t bring the mountain down to your level. The new generation of climbers don’t seem to feel that way at all - they think you shouldn’t have to take unnecessary risk to climb a classic route.

https://gripped.com/news/first-ascentionist-pushes-back-on-h...

I like this - I think you're not too far off of what's popular these days though. I think similar functionality can be achieved by using the "hook" functionality in claude code / codex.

I've been using both on a Rust codebase and have found both work fairly well. Claude code is definitely more capable than Gemini. What difficulties have you had?

The biggest pain point I've had is that both tools will try to guess the API of a crate instead of referencing the documentation. I've tried adding an MCP for this but have had mixed results.

https://github.com/d6e/cratedocs-mcp

Congrats on the launch! This is really cool - one of the applications of LLM I find most compelling. I've seen so many back office processes that have hundreds of steps, are incredibly error prone, and traditionally couldn't be automated due to API limitations. Solutions like Skyvern are going to supercharge businesses that have had historically low margins due to the number of humans required. (Not as a replacement for a human, but as a force multiplier)

Only if you require text message based two factor. Password managers like 1Password allow you to store your OTP within them and share that + the password internally within your team

Nice work on this! I love that it has a lightweight backlog built in and that I can describe what my current task is.

One small feedback- the motion design is waaay too much. You should consider dialing it back 2-3x.

Thanks! Came to this thread hoping for something like these. They look useful!

Their CTO did a demo of TimeGPT at their launch event last month [1]. It definitely appears to be a very easy tool to use. Love that it's zero shot!

Regardless, need to see more benchmarks to better understand its true performance. If it holds up it would be a big win for time forecasting.

[1] https://www.youtube.com/watch?v=n7luRRyxLoQ

This is really great. Congrats on shipping it! You might find https://www.lingq.com helpful as a source of inspiration. I think it's a fairly similar concept.

LingQ's killer feature for me is that as you click on words (or phrases - which I find really helpful btw) to translate them, they are added to your vocabulary list. It will automatically create flashcards for you from this list for SRS. Plus when you're reading a new story, words that are in your vocab list are highlighted yellow and new words are highlighted blue.

You might be interested in this https://www.59breaths.app/

There is a large graveyard of startups that have tried to crack open this market. It's a quite hard concept to execute on.

Some companies have made headway in eyewear and shoes (https://www.amazon.com/b?node=23595320011). Clothing is much more difficult - a lot of variety in body shape to accommodate.

He believes proof of humanity is vital in a world where AI can convincingly pass as human

Mate, trust me that San Franciscans are quick to pop their shoes off at the door haha

This looks cool! Is it possible to feed the output of one cell into the input of the next? That would really unlock the value of a tool like this for me.

I was just looking into this earlier. A lot of major packages have explicitly stated 3.11 readiness, but we're still only at 45% of the top 360 packages.

That's not to say the remaining 55% are broken on 3.11, just tread with caution. For comparison, 71% explicitly support 3.10.

https://pyreadiness.org/3.11/

Running over in Rodeo valley (Marin) there was a very noticeable (and unusual) inversion this morning around 7:30 am. It must have been 5-10 degrees colder on the valley floor compared to up higher -- after ~100ft of elevation gain up out of the valley it warmed up very rapidly.

I don't see that reflected in this map at all fwiw. https://sf.atmo.ai/[email protected],-122.51075,13.53,20,...

wow small world- you have a poster up in your window with the URL, right? i think you live around the corner from me!

This is awesome. I've been abusing Zapier for years now as a middle layer to integrate with 3rd parties without having to implement their APIs. Zapier's UI is built for non-technical users, anad it makes a lot of advanced use cases very cumbersome to implement.. Super excited to try reimplementing some of our more complicated zaps with this!

Are you all planning to implement as extensive of a collection of integrations as Zapier has?

hey, congrats on launching- the demo is impressive :)

at unspun.io our customers create a body scan and we use that to make completely custom garments.

have you all considered supporting a use case similar to ours: virtual try-on with a 3d model as the input instead of user uploaded image?

The state of the art [1] for body fat estimation using depth sensing is actually quite good (R2 value of 0.78).

The hard part will be accurately extracting the anthropometric features from the front/side/back images that Halo captures. There's a chance they would initially launch an iPhone only app and leverage the face scanning depth sensor.

[1] https://www.nature.com/articles/s41430-020-0603-x

That's true. But the prices just keep going up -- they increased their prices across the board by 30% this year.