mcast

This harness also burns a lot more tokens than Pi, which sort of kills the minimal philosophy/system prompt that Pi came from.

It's a shame the labs don't open source their models after deprecating them. I get why, but, it's a piece of internet history I hope is preserved.

It seems deeply suspicious that a company benefitting from regulatory capture would artificially stoke fears of AI and propaganda about it.

When you search "us passport" or "tsa precheck" on Google, you constantly see promoted ad results impersonating government sites (ie passportvisarush.com or easegov.com) extracting and selling your PII (social security number, etc) from your application.

I've reported the ads multiple times, but new ones still end up being promoted. I'm sure these companies have mined and sold thousands of SSN/address/DOB info from unsuspecting users.

It’s a trustworthy name for enterprises. Many executives are old enough that IBM was the Google of their time when they started their careers.

Interesting timing to release this on the same day Jensen makes a statement on open source AI.

Google and Amazon both have incredibly large compute deals with frontier labs and GovCloud. They may not want to sour on that cash.

That ship has sailed, I would wager all the AI labs are ingesting anything human generated, whether that means Hollywood movies, Taylor Swift’s discography, YouTube videos or private GitHub source repos.

The reward for having a competitive edge is exponentially higher than the risk of a lawsuit. Politicians are still old bureaucrats who don’t understand technology.

TikTok wasn’t open source and able to be run on your own hardware. Banning Alibaba’s models (or even a personal fork of them) running on your machines seems hard to defend in court.

Is there any SCOTUS precedent for this? It seems like a huge 1A issue for the government to limit self hosted access to a foreign country’s LLM.

Stripe seems to be doing fairly well as a private company. They continually offer liquidity events for employees to cash out, while also retaining less pressure for hypergrowth from outside activists and investors.

It sounds like Anthropic is dangerously low on compute availability if they’re prioritizing these refusals as their OKRs.

I've been very content moving away from OneDrive/GDrive to a personal NAS setup with Synology/Ugreen. You can access a shared drive/photo drive and use Tailscale to mount your volume from anywhere.

I've also configured encrypted cloud backups to a different geographic region and off-site backups to a friend's NAS (following the 3-2-1 backup rule). It does help having 2.5Gb networking as well, but owning your data is more important in the coming age of sloppy/degrading infrastructure and ransomware attacks.

Lockdown mode is opt-in only though

I guess this is a bullish sign OpenAI has hired a lot of PMs from Google!

>repeated rounds of cuts are destructive to morale, to focus, and to the trust [...] i'd rather take a hard, clear action now [...] than manage a slow reduction of people toward the same outcome

I think this is pretty agreeable, spanning layoffs into a monthly/quarterly "Hunger Games" is very damaging to employee morale.

Using OAuth tokens from Claude Code/Claude.ai in third party tools such as OpenClaw or OpenCode now officially warrants a ToS violation.

https://x.com/robzolkos/status/2024125323755884919?s=46

Selecting your own mute words for your timeline is the best part about Twitter. The algorithm changes have been pretty bad in the last few weeks though.

I should note this only happens in Claude Code, not the web UI. Since CC is agentic and spawns subagents on prompts that require a lot of thinking.

It will spend a lot of time grokking the codebase, which would consume more tokens on larger projects.

It's known that Anthropic's $20 Pro subscription is a gateway plan to their $100 Max subscription, since you'll easily burn your token rate on a single prompt or two. Meanwhile, I've had ample usage testing out Codex on the basic $20 ChatGPT Plus plan without a problem.

As for Anthropic's $100 Max subscription, it's almost always better to start new sessions for tasks since a long conversation will burn your 5-hour usage limit with just a few prompts (assuming they read many files). It's also best to start planning first with Claude, providing line numbers and exact file paths prior, and drilling down the requirements before you start any implementation.

I’m not surprised they closed the loophole, it always felt a little hacky using an Anthropic monthly sub as an API with a spoofed prompt (“You are Claude Code, Anthropic's official CLI for Claude”) with OpenCode.

Google will probably close off their Antigravity models to 3P tools as well.

This is not much different than a smarter WebMD, if anything, more doctors are using ChatGPT with their patients today than you realize anyway.

Not to mention, doctors are absolutely fallible and misdiagnose constantly.

It’s incredibly impressive to see a large company with over 30x as many employees (or 2x if you compare with GDM) than OAI step back into the AI race compared to where they were with Bard a few years ago.

Google has proved it doesn’t want to be the next IBM or Microsoft.

Better yet, setup transaction alerts on all your credit cards, and use a budgeting app like Monarch/YNAB to review all your household transactions each month or receive weekly email summaries.

I agree, but a lot of petty/non-violent crime isn't enforced or reported anymore.

The subway systems is one of the greatest socioeconomic equalizers in NYC. During rush hour, you'll share a subway car with a homeless man, an ER doctor wearing scrubs, a fashion model wearing YSL, a finance bro, and a food delivery worker. It's an amazing city for people watching.

There might be a future market for proctored classrooms for adults taking interviews.

Or maybe companies will ship a special “interview video kit” that will include having a candidate setup a tripod and camera recording their screen.

The difference is Tesla had a moat with the electric car market, there were no affordable and practical EVs 10 years ago. OpenAI is surrounded by competition and Meta is constantly releasing Llama weights to break up any closed source monopolies.

Trent Reznor and David Fincher need to team up again to make a movie about this.

It's pretty insane to see remote detonation technology used and implemented in 1996, considering cell phones looked like Nokia bricks and the RF hardware needed to implement this needs to fit in a pretty tight space in the phone.