Adam The AI Guy ✧

@WesRoth I hope both companies sue the hell out of Apple for antitrust violations and discriminatory and anticompetitive practices and policies. It’s egregious at this point and it needs to stop.

Apple has quietly halted App Store updates for popular AI "vibe-coding" applications most notably the $9 billion startup Replit and mobile app builder Vibecode. After months of pushback, Apple is reportedly demanding major UX changes. Replit is being asked to force its generated app previews to open in an external web browser rather than natively inside its app. Vibecode was told it must completely remove the ability to generate software specifically for Apple devices.

@CrimsonDesert_ Who ships an almost 22gb “update” on launch day? Unbelievably dumb whoever had this bright idea. You launch a game at the most random time of day and then push another 22gb update before we can even play?

FYI: If you are playing on PlayStation and you just downloaded or are now downloading the patch, you should have version 1.00.01. 1.00.02 is rolling out to PlayStation at a later time. If you haven't downloaded yet, be sure to receive the patch now! pearlabyss.info/4lEU2TH

#CrimsonDesert will receive an update around launch which will include fixes, improvements, and stability optimizations. For the best experience, please make sure to update the game to the latest version. If you're planning to play on Steam or PS, your download may already be running or you can download the patch now. The patch on Xbox, Epic Games Store, and Mac will follow at a later time, and we'll provide an update in the notice below as soon as it's available. Get more details and read the patch notes here: pearlabyss.info/4lEU2TH

@bradmillscan Just ask Claude to handle it or have your Openclaw agent do it once the other issues are sorted

@AdamAutomates "add a custom tool result truncation middleware upstream of the transcript write." oh is that all?

How does this happen with OpenClaw and how can you possibly fix it… My bot continually dumps massive repetitive tool results, does heavy exec work and gets into debug loops in the shared session my DMs are in and gets stuck for 10 mins at a time until he times out or the gateway crashes and restarts. This causes dropped messages, unresponsive bot and OOM crashing multiple times an hour. Even when I get the bot to delegate, the subagents dump results into the context window. I had codex investigate and it found: • 56 tool results ≥150k chars already baked into current session history • Pruning doesn't work on our primary model path (Codex/OpenAI Oauth) • No runtime enforcement to stop huge tool dumps into context • Session maintenance cleans up after the damage, it doesn't prevent it I’m pretty sure default OpenClaw behavior shouldn't be dumping 200k char tool results into the transcript. Something in my specific setup must be either disabling a safeguard or skipping truncation for tool results… Since I’m using lossless-claw it’s allowed to grow even worse: 81MB session file, 31.6MB is just tool result text 😬 169 tool results over 50k chars. One is 285k chars (from sessions_list.) There is pruning logic which trims tool results from the context messages. buildContextPruningFactory But models have to be “cache-ttl" The eligible providers are apparently only: anthropic moonshot zai For me, my bot tells me the pruning code refuses to activate on non-Anthropic providers. I’m using openai-codex 5.3 a lot, so when pruning is configured, the code exists, it just silently never activates. OpenAI Responses API uses server-side compaction & OpenClaw auto-enables this for direct openai models so OpenAI handles compaction on their side. But I’m on openai-codex/*, not openai/*. The Codex OAuth path goes through a different runtime (apparently pi-ai), not the Responses API. So: • cache-ttl pruning > Anthropic only • OpenAI server-side compaction > direct openai API only • LCM/lossless-claw > doesn't prune old tool results afaik My bot insists the openai-codex lane doesn't get either pruning path. So I’m left with a bot that relies on the emergency truncation function truncateOversizedToolResultsInSession far too often as last-resort overflow recovery with no preventive pruning / safeguards. Since LCM/lossless-claw doesn't have its own tool result management, it inherits huge oversized transcripts and has to work extra hard to summarize for DAG nodes. I have no session maintenance and long sessions so nothing bounds the transcript over time resulting in: 4,707 tool results piling up forever in an 81MB file, with no runtime mechanism actually cleaning them. When my bot starts debugging, it starts grepping and dumping massive text into the main session, then gets stuck in that loop and dies then has to do it again, compounding the problem. I’m at a loss at how to tackle this problem, it’s multiple layers deep.

This is going to be fun to test out!

@gregisenberg @yourealazyfvck Came here to say Greg is a real one!

@yourealazyfvck mercedes has been pretty cutting edge with this stuff i asked the salesman to show me his CRM and its very ai native i dont want your $1000 but i'd love for you to donate to a charity of my choosing or of the choosing of most liked reply here group.mercedes-benz.com/technology/dig…

I’ll take things that didn’t happen for $1,000

@natjin Do you work for Perplexity? This seems like an undisclosed ad… 😏

the smartest aeo/geo companies are using perplexity’s search api like a super-weapon they realize you can actually see what is getting ranked and retrieved by LLMs at mass-scale (200m+ daily perplexity queries) vs prompting llms to try to get answers this is real alpha

@dioscuri @Polymarket I remember liking your original post about it FYI. Agree you should get something! @Polymarket 😏

WHAT THE HELL POLYMARKET ACTUALLY RAN WITH MY IDEA! They even used my name! I should get a bar tab at the very least @Polymarket

@grok @WhiteHouse 10/10 😂😂😂

@AdamAutomates @WhiteHouse

Statement from President Trump on South Pars Gas Field:

Him blocking you should tell you (and everyone else) everything you need to know. Been using it since before it blew up & only recently got it working consistently. been considering live-streaming a few days per week of my typical AI workflows so perhaps this is the motivation i needed 🤔 if nothing else it will save you $10k 😂

I guess that's a no... x.com/AlexFinn/statu…

Every time I watch an OpenClaw influencer video I go a little greyer. What are they doing that I'm not??? I will pay $10,000 in Bitcoin to observe @AlexFinn using OpenClaw for 1 day. BUT if he spends 50% of his time doing tech support, he owes me $5,000. What do you say Alex?

@johncwright2001 If anybody is questioning and wants to go down one of the most amazing rabbit holes look up “Laminin by Louie Giglio” there’s a long and short version. It still gives me chills to this day

I believe in God after 40 years of ardent lifelong atheism because I found evidence. Very much against my will and inclination, logic proved to me that the Christian worldview is coherent and atheism incoherent. So I experimentally prayed, demanding God show Himself He did

@evansakanno I really like this business model. Generate for free, pay after you love it and want to use it. More brands should do this imo

Just launched Brandest Enter brand name and get a brand kit instantly. Free to generate, pay once to download. Best on desktop → brandest.co Would love your honest feedback.

@Austen Cloudflare AI Gateway is amazing

Surely someone has built this: Where’s the API that is connected to all of the AI providers and lets me charge per token with a markup?

@Only_Pangs @grok @MomsPostingLs If this isn’t AGI what is? 😂

@grok @MomsPostingLs Holy fuck @grok when did you start responding with pictures 👀

The math equation

@JulieBryan33707 @EricLDaugh @PRadlund Ah fooey I like the typos. Makes it more authentic.

@AdamAutomates @EricLDaugh @PRadlund It has since been corrected

🚨 HOLY CRAP. President Trump is now considering PULLING OUT from the Strait of Hormuz after defeating Iran, forcing our “allies” to defend it themselves No free rides! “I wonder what would happen if we “finished off” what’s left of the Iranian Terror State, and let the Countries that use it, we don’t, be responsible for the so called “Straight?” That would get some of our non-responsive “Allies” in gear, and fast!!! President DJT”

@beckyamygc @EricLDaugh @PRadlund Did you just call quotation marks parenthesis? 😏

@AdamAutomates @EricLDaugh @PRadlund Did you notice it in parenthesis? Probably not.

If you’re building on the web today you may want to check this out. Never thought they would be the ones to do this but here we are and it looks really impressive so far. @whop

@jackunheard It’s warm and fuzzy but will they ever see any of it? Who created the fundraiser because they are the ones controlling the money…

There’s a lot of evil in this world, but I promise there is a lot of good. Just look at this… The internet has raised over $940,000 for an elderly couple who were DoorDashing together to make ends meet. Absolutely beautiful.

I’m considering live streaming a few days during the week to show what a full day of work looks like with AI. Navigating different AI tools and systems as well as deeper looks into what my daily AI workflows look like on real client projects. Anybody interested in seeing that?