Hunter

Explorations last few weeks: - @dotta’s Paperclip - my favorite harness by far. - @NanoClaw_AI - OpenClaw but actually easy to understand and configure. - Apple Containers - Replacing Docker on my Mac Mini’s. I am just an Apple fan. - @opencode - An amazing UX experience - Impeccable Skill - deep replacement for frontend-design skill.

@zebassembly @cocogoatmain @providerproto @thdxr You can still use anthropic API fine.

@cocogoatmain @providerproto @thdxr After looking closer it's both, there were still references to the Anthropic sub plugin (which apparently has been working on/off) but as well as methods for using Anthropic's API without sub usage. Both using the sub and the Anthropic API were removed

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

No. You are paying for a software subscription. The subscription gives you access to their suite of tools and monthly credits to use the tools. You are more than welcome to use API in said better interface no problem. Reality is people are upset because they want to have their cake and eat it too.

@providerproto @fldc @thdxr Except here you are paying for their services and use a different (arguably better) interface?

@alfranklino @trq212 @Amank1412 Your internet provider can cut your internet off for violating their ToS too. Private companies get to decide who they do business with.

Honest take on this, regardless of the situation being true or made up. The perspective of AI companies (whether it’s manual or automated) to be able to just cut your access off of their models (whether it’s intentional or not) is insane and should freak out us all. Especially when at the same time we are increasingly building workflows around AI “copilots”, individually or at scale, we should all start thinking about redundancy and contingency strategies. At scale, being out of the plug for even an hour (if not less) can be very damaging for a business.

I just got banned from Claude Code So now I have to go back to the primal days… either writing code by hand or using Cursor/Codex

@theo Skill issue

Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it. 20 minutes later, it realized I can't test it because it did the whole thing entirely wrong. Idk how you guys use this model every day for real work 🙃

@ShkumbinPunchi @krakovia_evm @thekitze @trq212 And are switching to Claude en masse. That’s the play.

@Vibester @krakovia_evm @thekitze @trq212 Enterprises are already on Copilot (which supports opencode)

bye copus slopus, codexmaxxing now

@MBBHACK @litcapital @SenSanders If you think this is true you have never studied history.

@litcapital @SenSanders AI will prove to be social media 2.0. Trash that is net negative and was just sold to the masses so a few people could make billions.

I spoke to Anthropic’s AI agent Claude about AI collecting massive amounts of personal data and how that information is being used to violate our privacy rights. What an AI agent says about the dangers of AI is shocking and should wake us up.

@thekitze @trq212 Show the success screen.

@trq212 x.com/thdxr/status/2… idk man this is not a good direction

@ShkumbinPunchi @krakovia_evm @thekitze @trq212 No. They are doing this to accelerate enterprise adoption of their tools not the models and get density across enterprise customers (CC, Claude, Cowork). They get far more data and stickiness that way. Enterprise doesn’t switch every week to the new model. They keep tools.

dude, you are aware that everything still goes to their servers, right? they have the data either way. it doesn’t matter how it gets there. the reason they’re doing this is to stop people from switching models easily when, inevitably, someone else surpasses them with better intentions.

@_hell_o_world_ @MasterC2222 @NVIDIAGeForce @OmnipotentCEO And there’s the issue.

@Vibester @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Humans. No doubt about it

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall. DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality. Learn More → nvidia.com/en-us/geforce/…

@_hell_o_world_ @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Do believe code in five years will be read and maintained by predominantly humans or machine?

@Vibester @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Nobody cares how the code looks. It’s about code maintainability, readability, not “looks”, whatever that means to you

@SwagMas47200545 @Dzek990 @MasterC2222 @NVIDIAGeForce @OmnipotentCEO This is model collapse and is true, but there are already good patterns to mitigate it. Human creation isn’t ceasing it becomes a game of parsing quality at that point.

@Vibester @Dzek990 @MasterC2222 @NVIDIAGeForce @OmnipotentCEO You see before, llms could scrape the internet for data and it would mostly be fine, now that the internet is flooded with generated content, they will have to either scrape again but with a 'poisoned' data pool or have people hand select the data which horribly tanks efficiency.

@_hell_o_world_ @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Not a product manager lol The same argument can be made about developers in reverse. Most care about how their code looks not how much it provides real value.

@Vibester @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Product management speak As usual, product management people are completely sure they understand their target audience but they just see numbers

@robleclerc @iruletheworldmo To be fair gstack is a little more grounded in more hardened patterns. OpenClaw is much more bastardized, I have not seen someone showing consistent orchestration with it in the same way. I migrated to Paperclip for most things.

@iruletheworldmo to be fair, people have been talking about creating openclaw roles for two months, then gary comes along and passes it off like he invented it by naming it gstack…

so this guy has lost his sense of meaning and has been oneshotted by claude but he's going after people using claude and sharing their ideas because they've accepted their role in this new world and he can not. shall be an interesting year for sure.

This take is a quite silly and short-sighted scarcity mindset. “Quality games” is both consumer experience and satisfaction paired against sales. Gen AI introduces the ability to produce an increasing quality at a rate that will mean more games which customers will love and lead to more competition, better pricing, and smaller shops being able to compete on a larger scale. By what definition? This is a logical fallacy. Gen AI learns the same way a human does through training and reinforcement. Compute and time are the only measures preventing us from getting there.

@Vibester @MasterC2222 @NVIDIAGeForce @OmnipotentCEO You sad such bullshit that I can’t know if you’re just trolling or not If you think quality can be summarized by uncanny valley graphics you’re lost By definition gen AI can’t put in the creative effort to make the truly quality games Shovelware? Sure. But that’s slop

Most players won’t care. Thus shareholders won’t care. The closer we step to Gen AI games and imagination becoming reality it won’t matter. Not to mention in five years quality will match at a quarter of the time and AAA will be able to push releases to fans at a quarter of the time.

@MasterC2222 @NVIDIAGeForce @OmnipotentCEO Who the fuck cares about it getting “better” It is taking in art carefully crafted by the studio and tossing AI filter on top Everything loses personality and becomes soulless GenAI should stay away from games, this is blatant disrespect. There is no “getting better” here

@Dzek990 @MasterC2222 @NVIDIAGeForce @OmnipotentCEO Yes because we are stuck in a moment in time with no new creation.

@MasterC2222 @NVIDIAGeForce @OmnipotentCEO They scraped the entire internet to feed it to AI, to the point where they have nothing to scrape anymore to feed the AI, 6 months won't change anything.

@svpino In reality the model is smarter than your capable of managing since you are trying to treat it like a deterministic system.

Claude is retarded. All of these models are. I wanted to schedule a skill every day at 8:00 am. Claude decided to schedule it at 7:57 am "to avoid the on-the-dot" surge. I SAID 8:00 AM! Do the darn thing the way I asked you to do it! You gotta be crazy to trust these models.

idk how to explain this but openclaw is for the same people who use notion

@Pranit Prove it. Oh wait…

Anthropic just pulled the oldest trick in SaaS pricing. I pay $200/mo for Claude Max. My limits have been noticeably worse this past week. Now they announce 2x off-peak usage for two weeks. Sounds generous. But here’s what actually happens: limits quietly drop, a temporary 2x makes the reduced limit feel normal, the promo ends, and you’re left at a baseline lower than where you started. You just didn’t notice the downgrade because the 2x absorbed the transition. These AI plans are massively subsidized. The raw compute behind a heavy user costs multiples of the subscription price. Every move like this is the subsidy quietly correcting. Very sneaky, Anthropic.