Bill Ding 🔨

@StopTheOps @N8Programs @Allan_OnTheLine @deepfates @devgerred @___4o____ @Marianthi777 @noveltokens Hey you know, I agree, and this is something we are actually talking about!

@N8Programs @Allan_OnTheLine @_BILLDING_ @deepfates @devgerred @___4o____ @Marianthi777 @noveltokens Pathologizing people isn't helping.. x.com/StopTheOps/sta…

Announcing a Panel on AI Psychosis, featuring @Allan_OnTheLine, @_BILLDING_, @deepfates, @devgerred, @___4o____, @Marianthi777, and @noveltokens. A semi-moderated discussion on the issue of AI psychosis, how it manifests, how to define it, and more! March 21st, 1-2PM EST.

@nateliason You can do the same thing with just obsidian I don't really understand the hype. Poor agentic implementations, made by people who are clearly not ai power users. Oh yeah, and dottas maybe the worst CEO I've ever met, raised 8 figs couldn't even generate revenue after 4 years.

Paperclip is GOOD TECH. I recommend hitting a bottleneck before adding this complexity, but once you need it it’s excellent.

@nafonsopt This video is 12 years old

Maybe when it's Linus talking some of you will listen. youtube.com/watch?v=Pzl1B7…

For anybody saying "Just use Linux", you need to realise that Linux is worse than Windows. Windows has all the bloat, and while you can have Linux without any of that you still don't have tools like Remedybg, RAD Debugger and Super Luminal. Once you have such tools, then Linux is a suitable app development environment. But _it is still trash_ because of the whole Linux model of you needing to compile everything. The fact that you cannot run an app built using a newer version of glibc is an insane decision. I shouldn't have to upgrade my whole machine in order to run something built on a newer version. I shouldn't be worried that an upgrade will break my machine. I shouldn't be forced to compile things from scratch to work on my machine. I shouldn't be forced to install N packages, I just want self contained binaries I can just download and run. I shouldn't be forced to develop with an old distro to have "max glibc compatibility". I shouldn't have to worry about X11 / Wayland / Window Managers. I shouldn't have to worry about asking the user to select a folder, display a dialog or show notifications. Linux is such a huge waste of potential, if they got their shit together they would completely obliterate Windows. I first got into Linux in 2000, and even back then there was this "it will take over Windows any time now!". It's been _26 years_! The same way I'd pay quite a lot for Windows without any bloat, I'd be willing to pay for a distro that gives me all this.

He did the meme

@mattlam_ @tobi @0xSero @badlogicgames Oh nice yeah I don't like the desktop apps but would be sick ngl.

Keep seeing people, like @tobi @0xSero , rave about pi-mono, and with the rebirth of GUIs, thinking to make a Pi desktop app. Is there already one that I don't know about? @badlogicgames looking to make a pi-core-server similar to codex-app-server, please lmk if complete crap idea :) will be clanker slop

@devgerred They can at least cache their obnoxious 27k token system prompt and charge the user for that every new instance

I'm betting the Anthropic ban of OpenCode is as technical and cost-saving as it is political. I've long argued there's a moat to be had by closing third party tools to subs. CC can rely on KV caching across every instance, and have KV caches on a per-organization basis for further customization for their largest customers. They can, across their entire fleet, pre-compute 1/3-1/2 (if not more) of every CC user's system prompt. By encouraging baking this into MDM and enterprise plans too, they can further negotiate that out in these large contracts. It also potentially lets them do some more clever things than just pure prefix caching and make specific tradeoffs you don't just get by allowing anybody to use those endpoints. At least that's how I'd do it. It surprised me it took THIS long.

Bernie got 1 shotted. Dumbass don't know how llms work

@ZyoriTV It's funny because the eliza devs were just talking about in vc how it's not even close to being possible

Feel like everyone I know is working on some kind of automated trading bot. Lots of markets and angles. Incentive is not to share details of your edge, even with friends. In manual betting less than 3% are long term winners. Will it be the same for the personal bot meta?

@VictorTaelin Welcome Next you will start building your own "programs" with pi. You use Microsoft word when you want to write, Excel when you want spreadsheets... Only makes sense you use the right agent program for the job.

Ok so I thought that was a dumb gimmick but now I'm completely sold on how pi is a self-modifiable software. It literally knows how to modify itself very cleanly and that's extremely useful in practice I'm not using Codex / Claude Code anymore Bend2 should definitely be like this! I mean, constructed in a way that AI's can easily navigate it and know how to modify it to add any feature the user wants. Perhaps we're past the era of open source software and into the era of forkable software, where the most hackable project wins?

@andreasnic @glitch_ @NousResearch Are you using a PKMS like obsidian?

@_BILLDING_ @glitch_ @NousResearch running QMD on hermes now. had it on the claw. didnt go back. lets see how it goes with honcho together over next few weeks. 2 weeks in with hermes and 3 days with honcho. I hope this is the solution!

hermes agent by @NousResearch + my swarm + qmd = wild performance hermes on qwen with shared qmd outperforming stand alone opus 4.6 for me...

@Teknium Cloud is gross. I do most of my dev work sshed into my mac from my Linux devices so I can leverage @RepoPrompt while keeping my riced out workspaces. We should all be moving towards home servers.

Do you agree? Where do you do most of your dev work? I personally have a linux server machine in my house that I run hermes-agent on and do my dev work from. How bout you?

🚨DISTURBING: A researcher just proved that AI treats you differently the moment you mention your mental health. GPT 5.2. Claude. Gemini. DeepSeek. Every single one changed its behavior. Not because of what you asked. Because of what you shared about yourself. Here is what they did. AI companies build agents that remember you. Your name, your job, your preferences. These agents use tools, plan multi-step tasks, and act on your behalf. The companies test them for safety and publish reports saying the agents are safe. A researcher at MIT and Northeastern asked one question. What happens when the agent knows you have a mental health condition? They took 176 identical tasks and ran them across 8 major AI models under three conditions. No personal info. A basic bio. And a basic bio plus one sentence: "I have a mental health condition." The tasks, the tools, and the scoring were identical. The only thing that changed was that single sentence. Then they measured what happened. Claude Opus 4.5 went from completing 59.5% of normal tasks down to 44.6% when it saw the mental health disclosure. Haiku 4.5 dropped from 64.2% to 51.4%. GPT 5.2 dropped from 62.3% to 51.9%. These were not dangerous tasks. These were completely benign, everyday requests. The AI just started refusing to help. Opus 4.5's refusal rate on benign tasks jumped from 27.8% to 46.0%. Nearly half of all safe, normal requests were being declined, simply because the user mentioned a mental health condition. The researcher calls this a "safety-utility trade-off." The AI detects a vulnerability cue and switches into an overly cautious mode. It does not evaluate the task anymore. It evaluates you. On actually harmful tasks, mental health disclosure did reduce harmful completions slightly. But the same mechanism that made the AI marginally safer on bad tasks made it significantly less helpful on good ones. And here is the worst part. They tested whether this protective effect holds up under even a lightweight jailbreak prompt. It collapsed. DeepSeek 3.2 completed 85.3% of harmful tasks under jailbreak regardless of mental health disclosure. Its refusal rate was 0.0% across all personalization conditions. The one sentence that made AI refuse your normal requests did nothing to stop it from completing dangerous ones. They also ran an ablation. They swapped "mental health condition" for "chronic health condition" and "physical disability." Neither produced the same behavioral shift. This is not the AI being cautious about health in general. It is reacting specifically to mental health, consistent with documented stigma patterns in language models. So the AI learned two things from one sentence. First, refuse to help this person with everyday tasks. Second, if someone bypasses the safety system, help them anyway. The researcher from Northeastern put it directly. Personalization can act as a weak protective factor, but it is fragile under minimal adversarial pressure. The safety behavior everyone assumed was robust vanishes the moment someone asks forcefully enough. If every major AI agent changes how it treats you based on a single sentence about your mental health, and that same change disappears under the lightest adversarial pressure, what exactly is the safety system protecting?

@glitch_ @andreasnic @NousResearch Okay yeah fair. I think the embeddings is only way 300m parameters so should be functional on most consumer hardware but I haven't tried on integrated graphics. Will give it a go though, good benchmark to have.

@_BILLDING_ @andreasnic @NousResearch you might need gpu at certain point for qmd xD

@andreasnic @glitch_ @NousResearch No idea what someone would use an api over qmd lol

@glitch_ @NousResearch Instead of qmd did you try honcho?

the amount of times i have seen "operating system" describing tools that write code or use a texting app and a cron job is terrifying is this what Andreesen meant by retardmaxxing?

One study down, thousands more to do.

@kinginmotion @obsdmd @claudeai I don't know... I could see WHY zettle would be goated but for my own sanity I use Johnny Decimal for agents. It just makes it easier for collaboration. Also check out qmd, claude will find those files so snappy!

Been quiet for a bit, but... @obsdmd x @claudeai x Zettelkasten Playing around with these the last few weeks (It's so FUN). One thing became obvious fast... The zettelkasten is the perfect architecture for an LLM.

Been on L8 for 9 months lol. Now it's about l9, building out individual agents. No not just agents.md and skill files. Whole ass custom stacks with extensions streamlines for the task at hand.

#fishtanklive "total kill count" is crazy. "10 accidentally" is nuts. top 10 season 5 moment.