mritchie712

"whats next" is another good one

I'm not going to care about open models until some blend of the below becomes true:

1. the labs stop offering max plans

2. really smart open models can easily be run on my mac

3. TPS (token per second) AND intelligence are gpt5.6 level

on #1, it's nearly impossible for me to run out of codex tokens right now (I have 4 resets banked) and Fable 5 seems to be sticking around for the foreseeable future. I have virtually unlimited token usage for $400 a month, so open models being cheaper doesn't appeal to me.

on 2 and 3, benchmarks are showing some of the open models at around opus4.8 levels, which is incredible! But running them locally at anywhere near the TPS of cloud inference is far off. I can run a smaller (dumber) open model locally and get good TPS, but see #1, whats the point?

This is far cooler than how I've been using my Pi.

I've started building a box for managing agents. I hate sitting in front of my Mac all day flipping between terminals. I wanted something that was audio and whiteboard / paper first.

The Pi has a mic, camera, and projector hooked up. The Pi is always listening, so I just say most commands (i.e. "check logs on backend service, customer xyz said abc is wrong"). I can tell it "look at the board" and it can see things I've written or drawn and can project on top of or alongside anything on the board.

Not sure yet if it's more efficient, but it's definitely more fun.

here's how this likely went down:

1. they found the dataset and thought "i bet there are weird order combos i could write a blog post about"

2. they did all the analysis and found nothing all that interesting

3. posted it anyway

this works well when you don't have customers

great game, what do you think of adding shuffle?

if gpt5.6 is out by July 7th, Fable will stay in the Max plan to at least some degree.

There's another "they took our jobs" group that doesn't fit into "AI is overhyped" or "AI is useless".

They see that AI is capable and fear it.

I agree on opus 4.5-4.8, but Fable 5 was a noticeable upgrade.

Looks cool! It's a lot of work to get a full data stack set up and people are losing interest in stitching the pieces (ETL, warehouse, BI) together.

Agents made bad inferences because they had no context on the business

We've been working on this since before the chatgpt launch.

We started with a semantic layer since there were already good open source options and LLMs at the time were good at writing the JSON (remember function calling?) to run a semantic query.

But as LLMs have gotten smarter and people wanted to do more data work in agents, we found we needed something more flexible, so we built an "Ontology" that lets you store all the terms you use in your company and connect them to the data points (e.g. tables, columns, metrics) that matter.

https://www.definite.app/blog/ontology-ai-analytics

For anyone that doesn't use twitter:

I index all my local Claude Code sessions in DuckDB. I have 202,381 messages in the last 30 days.

There's been a steady increase since Opus 4.6 in the model saying "honest".

It probably shouldn't, but this bugs me.

Should I assume most of the time you're lying and you're being honest in this one message?

I was pumped in the first few hours of Fable where this had seemingly been "fixed". 100+ messages and no "honest" to be seen. But it didn't last.

Within a few hours, Fable proved itself to be the most honest model to date.

Here is the rate at which visible assistant text contained the string "honest" (case-insensitive), split by model:

  claude-fable-5:             25 / 1,397   = 1.7895%
  claude-opus-4-8:            83 / 5,818   = 1.4266%
  claude-opus-4-7:           163 / 16,432  = 0.9920%
  claude-opus-4-6:            18 / 5,877   = 0.3063%
  claude-haiku-4-5-20251001:   0 / 71      = 0.0000%
  claude-sonnet-4-6:           0 / 4       = 0.0000%

don't think that was there when I read it the first time

I wonder how this would be looked upon by the ever changing rules of claude code.

If someone from Anthropic sees this, would love to know if I can use my max plan here.

The day was to begin like any other, with Antigravity open

This unexpected shift completely broke my preferred workflow

it might not have been so unexpected if you knew you were one of ~15 people that start their day with Antigravity

for reference, Flipper Zero was $199.

does anyone know how much they're thinking for Flipper One?

already works now! just tried it out

Can I use DuckDB with Quack as the catalog database for DuckLake?

Not yet, but we are working on it!

Seems like a niche use case, but it's the one I'm most interested in.

Our lakehouse uses ducklake with postgres as the catalog. Seems like a DuckDB / Quack catalog would be an excellent alternative.

We previously had our (https://www.definite.app/) agent write reports / dashboards in a YAML spec that would get rendered by our frontend framework (i.e. charts and tables).

For example, user says "build a report with revenue and orders by month and show 100 most recent orders". The agent would write a spec that would get rendered by our frontend.

This runs fast, but we were drowning in feature requests for what the framework could render (e.g. "I don't want labels here", "I DO want labels there", "can this chart be a heatmap", etc.)

A few months ago, we let the agent just write HTML instead. It takes longer to generate, but you get unlimited customization.

There are a host of issues with the new approach (non-technical users debugging a monstrous app they created), but net-net our customers like it much better.

for reference, it's the 2nd fastest model tracked in the "Highlights" section of https://artificialanalysis.ai/

looks like you work at github.

I completely understand a "people who give a shit stick around" mentality if you work there, but you can't expect users who run a business on it to stick around if it's broken.

I don't like the "I canceled my x subscription" hype posts, but I did cancel Figma today. We've barely used it in months and this was the nail in the coffin.

I remembered this post from (only) 3 years ago:

Show HN: I've built a C# IDE, Runtime, and AppStore inside Excel

670 points | 179 comments

One of the main use cases was to analyze Excel data with SQL. I'm the kind of nerd that loves stuff like that, but stuff like that seems completely obsolete now.

[0] https://news.ycombinator.com/item?id=34516366

this was true a year ago, but if you give an agent a new spec to follow (e.g. a .md file), it will follow it.

we have a custom .yaml spec for data pipelines in our product and the agent follows it as well as anything in the training data.

while I agree you don't need to build a new thing "for agents", you can get them to understand new things, that are not in the training data, very easily.

The data infrastructure underneath it took two years.

yep, that's what Definite is for: https://www.definite.app/

All the data infra (datalake + ELT/ETL + dashboards) you need in 5 minutes.

tldr: this caches your S3 data in EFS.

we run datalakes using DuckLake and this sounds really useful. GCP should follow suit quickly.

I think this is a move to get business users paying consumption (per token) pricing for codex instead of a flat rate.

Hannes (one of the creators) had a pet duck

what's the use case for cortex? is anyone here using it?

We run a lakehouse product (https://www.definite.app/) and I still don't get who the user is for cortex. Our users are either:

non-technical: wants to use the agent we have built into our web app

technical: wants to use their own agent (e.g. claude, cursor) and connect via MCP / API.

why does snowflake need it's own agentic CLI?

claude code solved this about a month ago

I think you're reading it exactly right