alphabetting

>The government doesn’t have to ask NYT to restrict opinions.

This 1988 model of the flow of information in free societies and their media gatekeepers was probably correct. Nearly 40 years later it is not. The digital content flows in free societies is so diverse today that widely read content extremely critical of whichever parties or power-holders you'd like to read about is everywhere and easy to find. Not the case in authoritarian systems.

the agentic benchmarks for 3.1 indicate Gemini has caught up. the gains are big from 3.0 to 3.1.

For example the APEX-Agents benchmark for long time horizon investment banking, consulting and legal work:

1. Gemini 3.1 Pro - 33.2% 2. Opus 4.6 - 29.8% 3. GPT 5.2 Codex - 27.6% 4. Gemini Flash 3.0 - 24.0% 5. GPT 5.2 - 23.0% 6. Gemini 3.0 Pro - 18.0%

I doubt there was a condition on writing positively. Other people who tested have said this won't replace engines. https://togelius.blogspot.com/2025/08/genie-3-and-future-of-...

It definitely saves system prompts and has for some time.

The one other unique thing I use from them is the interactive mind maps. Like a table of contents on steroids

I found this prompt online and tweaking it for audio overviews works extremely well for me.

https://open.substack.com/pub/lawsen/p/notebooklm-podcasts-b...

Generate a deep technical briefing, not a light podcast overview. Focus on technical accuracy, comprehensive analysis, and extended duration, tailored for an expert listener. The listener has a technical background comparable to a research scientist on an AGI safety team at a leading AI lab. Use precise terminology found in the source materials. Aim for significant length and depth. Aspire to the comprehensiveness and duration of podcasts like 80,000 Hours, running for 2 hours or more.

Over half of Amazon's third party sellers are Chinese companies who regularly false report to dodge tariffs on their products in ways that American competitors can't. Amazon claims to police them but they're extremely reliant on them at this point and the Chinese sellers just start up new brands if penalized.

https://x.com/zackkanter/status/1908343624464576666

Google team said it was outside the training window fwiw

https://x.com/jack_w_rae/status/1907454713563426883

The elo jump and big benchmark gains could be justification

The fact they are reaching out to journos to read the logs seems really misguided. Like from a customer standpoint that's the worst industry you could reach out to for checking private messages lol

Good to see but brings to mind the deal they cut with China in 2016 https://news.ycombinator.com/item?id=29482351

Is the statement from Apple just PR or is this not a usable exploit?

"Based on our analysis, we do not believe this issue poses an immediate risk to our users."

https://www.bleepingcomputer.com/news/security/new-apple-cpu...

Isn't like 70% of current VR usage for adult content?

Nat Friedman organized testing of 300 different bay area food products. More information and top line takeaways here:

https://x.com/natfriedman/status/1872728491290189944

Here is link to this latest one: https://aistudio.google.com/app/prompts/new_chat?model=gemin...

1.5 Pro-002 came out a couple months ago.

What's disturbing? In all likelihood the close timing was world labs rushing to get their demo out the door knowing this was coming because they wouldn't get nearly the hype they did if this came before.

Seems like there's already a lot of slop on steam and I really doubt it will be difficult for quality content to be highlighted even if the amount of games increases 1000x or more

The case centered around Apple getting paid $20B a year for Google search placement. How is being forced to sell chrome related to that?

>The vulnerabilities, credited to Google’s TAG (Threat Analysis Group)

Do they find these by monitoring the brokers of zero days or analyzing devices of people who are being targeted?

Impressive video: https://twitter.com/alexandertmai/status/1841739387400552826

I clarified in a another post I mean for benchmarking standalone models, not ones fine-tuned for solving ARC

How so? I think if a team is fine-tuning specifically to beat ARC that could be true but when you look at Sonnet and o1 getting 20%, I think a standalone frontier model beating it would mean we are close or already at AGI.

This is best AGI benchmark out there in my opinion. Surprising results that underscore how good Sonnet is.

I know it's not their intention but this seemed like a great ad for Pixels

>It’s a lot easier to pay off your would-be competitors than it is to innovate. I’m hesitant to say that antitrust is good for its subjects, but Google does make you wonder.

This line would ring more true if Google hadn't invented transformers and a host of other ML breakthroughs to bolster search. Also not search related, but inventing self-driving cars and solving protein folding are innovations that benefit consumers greatly.

I'd bet Ben himself has compared Google to Bell Labs in the past. To argue they don't innovate is insane.

Id wager SEO/AI slop is a much bigger problem for Google than ad load for their userbase. Only 20% of queries have ads so 4 out of 5 times ads won't even be seen. But on those 4 out of 5 do have the chance of turning users away from Google with awful SEO optimized sites and AI slop.

> Character’s leaders told staff on Friday that investors would be bought out at a valuation of about $88 per share. That’s about 2.5 times the value of shares in Character’s 2023 Series A, which valued the company at $1 billion, they said.

https://www.theinformation.com/articles/google-hires-charact...

Google spending a boatload for Wiz looks smarter now