robbiemitchell

This is the company that still hasn't delivered FSD and never will because they won't add Lidar to the cars. They can't even drive Robotaxis at night -- why would they try to fly?

It's also the company that built crap Cybertrucks and the fake humanoid Bots controlled by people remotely.

They will never deliver this. It's an excuse to justify SpaceX rescuing Tesla. Meanwhile, SpaceX is primarily Starlink, a telecom company, masquerading as space exploration and AI.

This appears to be an excuse to rep your own AI startup.

I get a better first pass at code by asking it to write code at the level of a "staff level" or "principal" engineer.

For any task, whether code or a legal document, immediately asking "What can be done to make it better?" and/or "Are there any problems with this?" typically leads to improvement.

One helpful addition would be Requests Per Minute (RPM), which varies wildly and is critical for streaming use cases -- especially with Bedrock where the quota is account wide.

For training, would it be useful to stabilize the footage first?

> some gimmick

"key differentiator" and not necessarily easy to pull off or pay for

It wasn't even set up for success at selling.

After years of raising 3 kids, you would think if I ask to add diapers to the cart, it would know something. But no, it would just go with whatever is the top recommended, or first in a search, or something like that. Nothing using the brand or most recent sizes we purchased.

There was no serious attempt to drive real commerce. Instead, Alexa became full of recommendation slots that PMs would battle over. "I set that timer for you. Do you want to try the Yoga skill?"

On the other hand, they have taken on messy problems and solved them well, but not using technology, and for no real financial gain. For example, if you ask for the score of the Tigers game, Alexa has to reconcile which "Tigers" sports team you mean among both your own geography and the worldwide teams, at all levels from worldwide to local, across all sports, might have had games of interest. People worked behind the scenes to manage this manually, tracking teams of interest and filling intent slots daily.

Asking even a top-notch LLM to output well formed JSON simply fails sometimes. And when you’re running LLMs at high volume in the background, you can’t use the best available until the last mile.

You work around it with post-processing and retries. But it’s still a bit brittle given how much stuff happens downstream without supervision.

Processing high volumes of unstructured data (text)… we’re using a STAG architecture.

- Generate targeted LLM micro summaries of every record (ticket, call, etc.) continually

- Use layers of regex, semantic embeddings, and scoring enrichments to identify report rows (pivots on aggregates) worth attention, running on a schedule

- Proactively explain each report row by identifying what’s unusual about it and LLM summarizing a subset of the microsummaries.

- Push the result to webhook

Lack of JSON schema restriction is a significant barrier to entry on hooking LLMs up to a multi step process.

Another is preventing LLMs from adding intro or conclusion text.

It is workable. It’s like $6/month.

The real problem is that most people don’t want to pay for things.

As a Zapier user looking to go with something private for new use cases, how does this compare to an on-prem n8n.io?

This is a huge bummer! I wonder why they removed the playlist station feature.

You can do this in Spotify now by creating a playlist and then playing the station driven from that playlist.