RSS Parrot

BETA

🦜 Mario Zechner / @badlogicgames

@nitter.net.badlogicgames@rss-parrot.net

I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.

---

Twitter feed for: @badlogicgames. Generated by https://nitter.net

Your feed and you don't want it here? Just e-mail the birb.

Site URL: nitter.net/badlogicgames

Feed URL: nitter.net/badlogicgames/rss

Posts: 85

Followers: 3

ah, the great filter. https://www.theguardian.com/science/2026/aug/06/safety-fears-as-scientists-make-first-viruses-designed-by-ai

https://nitter.net/badlogicgames/status/2085500255248822380#m

Published: August 6, 2026 22:56

ah, the great filter. theguardian.com/science/2026… Link Safety fears as scientists make first viruses designed by AI Researchers say breakthrough offers hope for new medicines but also raises urgent biosecurity questions theguardian.com

RT by @badlogicgames: @PrimeIntellect did PI-pi, so here i am doing pi-PI. introducing pi-rlm prime intellect did a thing i wanted to do for a long time, they fused a stateful jupyter kernel with an agent. pi-rlm is that idea on top of bun and typescript. it takes over all of your available tools and swallows them into a single tool called `execute`, which runs code in a persistent evaluator. a single-tool pi that does everything. shell is Bun.$, pi's own tools are mounted inside as tools.*, subagents are a function call that returns a handle. @badlogicgames's pi stays untouched until you ask for it: pi install npm:@shift-labs/pi-rlm pi --rlm (btw variables survive across turns, sessions, and restarts, have fun)

https://nitter.net/micLivs/status/2085495732002275601#m

Published: August 6, 2026 22:38

@PrimeIntellect did PI-pi, so here i am doing pi-PI. introducing pi-rlm prime intellect did a thing i wanted to do for a long time, they fused a stateful jupyter kernel with an agent. pi-rlm is that idea on top of bun and typescript. it takes over all…

R to @badlogicgames: nothing wrong with getting started with a waveshare gadget you just plug in and have the agent program it. but i guarantee you'll find more fulfillment getting your hands and brain dirty instead of asking your agent to program a thing for a prebuilt usb connected device.

https://nitter.net/badlogicgames/status/2085490057134174479#m

Published: August 6, 2026 22:15

nothing wrong with getting started with a waveshare gadget you just plug in and have the agent program it. but i guarantee you'll find more fulfillment getting your hands and brain dirty instead of asking your agent to program a thing for a prebuilt usb…

recommended reading. i would also warmly recommend getting into electronics, do some soldering, some PCB design. you can teach yourself in 6 months, don't need a lot of gear. feels great slapping together a bunch of resistors, caps and ICs onto a PCB and have it work first time after a 1 week wait for a package from China.

https://nitter.net/badlogicgames/status/2085485450832273579#m

Published: August 6, 2026 21:57

recommended reading. i would also warmly recommend getting into electronics, do some soldering, some PCB design. you can teach yourself in 6 months, don't need a lot of gear. feels great slapping together a bunch of resistors, caps and ICs onto a PCB and…

recommended reading. another bookmark. (i, for one, am just not a fan of regulatory capture, mono-, duo-, and oligopolies. hate crypto too)

https://nitter.net/badlogicgames/status/2085471213145493660#m

Published: August 6, 2026 21:00

recommended reading. another bookmark. (i, for one, am just not a fan of regulatory capture, mono-, duo-, and oligopolies. hate crypto too) Dean W. Ball (@deanwball) no macro-technology birthed by the bay area tech industry has been met with more…

R to @badlogicgames: after reading the spec, this actually solves nothing. and the rest of us not in the blessed in-group now has to feal with another mess. just like with the skills "standard", which to date nobody has implemented properly, because for that you basically have to reverse Claude Code's slop. we should stop calling our shit engineering.

https://nitter.net/badlogicgames/status/2085426468285493454#m

Published: August 6, 2026 18:03

after reading the spec, this actually solves nothing. and the rest of us not in the blessed in-group now has to feal with another mess. just like with the skills "standard", which to date nobody has implemented properly, because for that you basically…

oh no, a new agent standard. bracing for impact. skills are still not namespaced afaict.

https://nitter.net/badlogicgames/status/2085413584582918540#m

Published: August 6, 2026 17:11

oh no, a new agent standard. bracing for impact. skills are still not namespaced afaict. OpenAI Developers (@OpenAIDevs) Build a plugin once and use it across compatible agent clients. Introducing Agent Plugins, an open standard developed with…

RT by @badlogicgames: check https://github.com/h4ckf0r0day/obscura

https://nitter.net/giuseppegurgone/status/2085383033989800008#m

Published: August 6, 2026 15:10

check github.com/h4ckf0r0day/obscu… Link GitHub - h4ckf0r0day/obscura: The headless browser for AI agents and web scraping The headless browser for AI agents and web scraping - h4ckf0r0day/obscura github.com

wtf

https://nitter.net/badlogicgames/status/2085377128598577458#m

Published: August 6, 2026 14:47

wtf Kenton Varda (@KentonVarda) It turns out you can run a full browser implementation in a Worker. No container needed. I didn't believe it myself when they first told me. Absolutely crazy project. blog.cloudflare.com/kitesurf… Link Introducing…

recommended reading. especially if you think a permission dialog is a great security model for agents. (they are not, which is why pi doesn't have that security theater built in) https://scalex.dev/blog/ai-agent-permissions-stats/

https://nitter.net/badlogicgames/status/2085377067273576912#m

Published: August 6, 2026 14:46

recommended reading. especially if you think a permission dialog is a great security model for agents. (they are not, which is why pi doesn't have that security theater built in) scalex.dev/blog/ai-agent-per… Link Humans missed 1 in 3 threats…

recommended reading. fun to see @phoboslab is still doing neat stuff. https://phoboslab.org/log/2026/08/xibalba64-making-of

https://nitter.net/badlogicgames/status/2085329597978018069#m

Published: August 6, 2026 11:38

recommended reading. fun to see @phoboslab is still doing neat stuff. phoboslab.org/log/2026/08/xi…

Gif

https://nitter.net/badlogicgames/status/2085261409768665388#m

Published: August 6, 2026 07:07

MTS (@MTSlive) MIT PhD student Alex Zhang on why simple harness abstractions beat models trained around their own harness: "When these abstractions are implemented in a really simple way, basically what you see with Prime Agent is that you can slot in…

love how the idea is catching on. (also has pi in it)

https://nitter.net/badlogicgames/status/2085118606308773940#m

Published: August 5, 2026 21:39

love how the idea is catching on. (also has pi in it) Sawyer Hood (@sawyerhood) my new daily driver for building software Article An Agentic IDE that builds itself I'm excited to show something I've been working on recently: bb, an agentic IDE that…

banger

https://nitter.net/badlogicgames/status/2085103130052612494#m

Published: August 5, 2026 20:38

banger Prime Intellect (@PrimeIntellect) Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable,…

PI + pi

https://nitter.net/badlogicgames/status/2085091341776605358#m

Published: August 5, 2026 19:51

PI + pi Prime Intellect (@PrimeIntellect) Prime Agent is built on pi and fully open-source with an open license github.com/PrimeIntellect-ai… Link GitHub - PrimeIntellect-ai/prime-agent: Prime Agent is a self-improving RLM agent that can be used...…

RT by @badlogicgames: Prime Agent is built on pi and fully open-source with an open license https://github.com/PrimeIntellect-ai/prime-agent

https://nitter.net/PrimeIntellect/status/2085087014710657496#m

Published: August 5, 2026 19:34

Prime Agent is built on pi and fully open-source with an open license github.com/PrimeIntellect-ai… Link GitHub - PrimeIntellect-ai/prime-agent: Prime Agent is a self-improving RLM agent that can be used... Prime Agent is a self-improving RLM agent…

RT by @badlogicgames: Prime Agent was designed as a coding agent, but also can be used for general agentic tasks in any domain. Prime Agent can autonomously run on challenging long-horizon settings like Factorio and MazeBench and yield strong results relative to existing harnesses.

https://nitter.net/PrimeIntellect/status/2085087012500177348#m

Published: August 5, 2026 19:34

Prime Agent was designed as a coding agent, but also can be used for general agentic tasks in any domain. Prime Agent can autonomously run on challenging long-horizon settings like Factorio and MazeBench and yield strong results relative to existing…

hrm, deepmind has done amazing things, and i really like hassabis' way of thinking about the entire field. we'll see.

https://nitter.net/badlogicgames/status/2085037320286114229#m

Published: August 5, 2026 16:16

hrm, deepmind has done amazing things, and i really like hassabis' way of thinking about the entire field. we'll see. leo 🐾 (@synthwavedd) 🚨 BREAKING: Demis Hassabis is stepping down as CEO of DeepMind and will take on a new role as Chairman, while…

Image

https://nitter.net/badlogicgames/status/2084991091544101328#m

Published: August 5, 2026 13:13

OpenRouter (@OpenRouter) Introducing Ori Harness: the easiest way to use your favorite harness with OpenRouter. Ori configures Codex, Claude Code, OpenCode, and Hermes out of the box to work with OpenRouter, with settings optimized per harness, for any…

recommended reading!

https://nitter.net/badlogicgames/status/2084929164839121265#m

Published: August 5, 2026 09:07

recommended reading! R 'Nearest' Nabors (@rachelnabors) TLDR: I'll be building the agentic web from the trenches going forward Article You don't have to ask permission to make things I’ve been covering the Agentic Web on my blog by the same name…

lol

https://nitter.net/badlogicgames/status/2084869200573542529#m

Published: August 5, 2026 05:08

lol MTS (@MTSlive) SITUATION UPDATE: The White House has exempted open models from its new framework to test frontier AI capabilities before release, per Axios. — https://nitter.net/MTSlive/status/2084757892532740519#m

RT by @badlogicgames: One fun benefit of spending so much time with enterprises is you get to see the array of AI implementation strategies that exist in companies right now. Unlike the early innings of cloud where there were really only a couple deployment patterns available -including being limited by only a couple infra vendors existing- AI actually has a much wider range of approaches in the enterprise. If you ask 10 IT leaders what their coding agent strategy looks like, you get at least 5 different answers. If you ask about their end-user productivity agents, some have standardized on ChatGPT or Claude, others offer a choice of multiple solutions, and many have built their own orchestration layers for employees to use any model. For models, we know the big ones, but increasingly enterprises are experimenting with OSS models, or are at least immensely curious about OSS and would jump at the right offering that felt safe. And increasingly there’s a set of vertical models and agents that equally show up in enterprises for a range of tailored use-cases. For accessing data, some enterprises just have agents take on the role of the user, and others are setting up agent users that have their own identities. Some companies are setting up substantial guardrails on what agents can do, and others are putting responsibility on the user. Given this heterogeneity this early on at the start, it means we’re in for years of landscape changes. Anyone who’s predicting ultimate market outcomes already probably will be wrong as nothing has formally settled in yet. Lots of opportunity ahead.

https://nitter.net/levie/status/2084828773808239080#m

Published: August 5, 2026 02:28

One fun benefit of spending so much time with enterprises is you get to see the array of AI implementation strategies that exist in companies right now. Unlike the early innings of cloud where there were really only a couple deployment patterns available…

RT by @badlogicgames: still doing this! expanding the team further. join me *waves clock in face*

https://nitter.net/pingToven/status/2084822706998956049#m

Published: August 5, 2026 02:04

still doing this! expanding the team further. join me *waves clock in face* Toven (@pingToven) i am hir*ng for my team (provider operations) i need inference api nerds. i need the nerd who undestands why the interactions api needed to happen. i need…

RT by @badlogicgames: the reason that nobody is using agents is because they are still wildly unrealiable even including the wildly expensive frontier models that are far too expensive to put in a mass-market consumer product the reason it works for coding is because you have a six-figure-salary subject-matter-expert resource sitting there babysitting it all day (and still shipping slop)

https://nitter.net/0xblacklight/status/2084767296695026172#m

Published: August 4, 2026 22:23

the reason that nobody is using agents is because they are still wildly unrealiable even including the wildly expensive frontier models that are far too expensive to put in a mass-market consumer product the reason it works for coding is because you have…

first time praying to @thsottiaux to reset limits. also ok with only reseting my limits. i never ran into the limit before, i think i should get a reset.

https://nitter.net/badlogicgames/status/2084750779563327967#m

Published: August 4, 2026 21:18

first time praying to @thsottiaux to reset limits. also ok with only reseting my limits. i never ran into the limit before, i think i should get a reset.

PSA: on the latest npm incident.

https://nitter.net/badlogicgames/status/2084661050041831655#m

Published: August 4, 2026 15:21

PSA: on the latest npm incident. Mario Zechner (@badlogicgames) pi is not affected. I checked all manifests, lockfiles, the published shrinkwrap, and installed dependencies against the current 434-package IOC list. No affected package/version or…

we need orbs. with a better name.

https://nitter.net/badlogicgames/status/2084660017433592148#m

Published: August 4, 2026 15:17

we need orbs. with a better name. Armin Ronacher ⇌ (@mitsuhiko) Currently @badlogicgames is looking at @AmpCode and I'm just waiting until he tells us we need Orbs next. — https://nitter.net/mitsuhiko/status/2084658003601416252#m

recommended reading.

https://nitter.net/badlogicgames/status/2084653876796412326#m

Published: August 4, 2026 14:53

recommended reading. Thorsten Ball (@thorstenball) Everything has changed for us with orbs. My biggest struggle right now is figuring out how to make you see what we see. So I sat down and wrote about it: ampcode.com/notes/what-i-wan… Link What I…

gramps works in mysterious ways

https://nitter.net/badlogicgames/status/2084641207456547131#m

Published: August 4, 2026 14:02

gramps works in mysterious ways Thorsten Ball (@thorstenball) I knew there was a motive to it. We've had thousands of diet coke cans next to tens of laptops many times this year and no spill. Mario shows up, an hour later there's a spill... —…

tried sabotage on @thorstenball 's laptop with a can of pepsi. it was ineffective. the mission is ongoing.

https://nitter.net/badlogicgames/status/2084636628367098357#m

Published: August 4, 2026 13:44

tried sabotage on @thorstenball 's laptop with a can of pepsi. it was ineffective. the mission is ongoing.

so everybody is building chatboxes with connectors now.

https://nitter.net/badlogicgames/status/2084633292645503362#m

Published: August 4, 2026 13:31

so everybody is building chatboxes with connectors now. Cursor (@cursor_ai) Cursor can now read, write, and act across your Google Workspace. New plugins give agents direct access to Gmail, Google Drive, Calendar, Docs, and Sheets. —…

getting to see how the @AmpCode sausage is made. @thorstenball has a little waveshare esp32 thing with touchscreen. just tells it to build breakout for it. doesn't care about the stack (arduino instead of esp-idf). concerning. (try Amp! it's orbin time)

https://nitter.net/badlogicgames/status/2084632919448973391#m

Published: August 4, 2026 13:29

getting to see how the @AmpCode sausage is made. @thorstenball has a little waveshare esp32 thing with touchscreen. just tells it to build breakout for it. doesn't care about the stack (arduino instead of esp-idf). concerning. (try Amp! it's orbin time)

see that? tooting our own horn. tooting it very loud. toot toot.

https://nitter.net/badlogicgames/status/2084617615364780329#m

Published: August 4, 2026 12:29

see that? tooting our own horn. tooting it very loud. toot toot. Pi (@pidotdev) Over the past few months Pi has consistently shown up in benchmarks as the best harness for both cost and performance. Earendil engineer @cristinaponcela examines case…

i have entered orb space. everyone at @AmpCode is concerningly nice to me. i was even feed free pizza and pepsi.

https://nitter.net/badlogicgames/status/2084612727100559860#m

Published: August 4, 2026 12:09

i have entered orb space. everyone at @AmpCode is concerningly nice to me. i was even feed free pizza and pepsi.

RT by @badlogicgames: earendil.com/posts/session-p…

https://nitter.net/dillon_mulroy/status/2084494163677008329#m

Published: August 4, 2026 04:18

earendil.com/posts/session-p… Link The Session You Cannot Take With You | EARENDIL Inference APIs are filling sessions with encrypted reasoning, hidden search results, opaque compaction, and encrypted subagent messages. A growing form of lock-in.…

recommended reading (as a bookmark). i honestly don't know what to think. https://yegge.ai/essays/model-welfare/

https://nitter.net/badlogicgames/status/2084421546395705756#m

Published: August 3, 2026 23:29

recommended reading (as a bookmark). i honestly don't know what to think. yegge.ai/essays/model-welfar… Link The Shape of Things to Come, Part 2: Model Welfare for Agentic Engineers — Steve Yegge Part 2 of The Shape of Things to Come. Model welfare…

for shits and giggles, i created a subagent skill yesterday, instructing pi to spawn itself in interactive mode, while watching the session file for the final assistant message. i forgot about it. now sol is using the skill all the time to spawn review agents. RL goes hard.

https://nitter.net/badlogicgames/status/2084418803958452284#m

Published: August 3, 2026 23:19

for shits and giggles, i created a subagent skill yesterday, instructing pi to spawn itself in interactive mode, while watching the session file for the final assistant message. i forgot about it. now sol is using the skill all the time to spawn review…

recommended reading.

https://nitter.net/badlogicgames/status/2084017646958206982#m

Published: August 2, 2026 20:45

recommended reading. David Crawshaw (@davidcrawshaw) Machines create code now. That means machines can personalize your software, if it is open source. Closed source tools (like Claude Code) are now less desirable. blog.exe.dev/devtools-must-b… Link …

recommended reading. if we get "stuck" with improvements in verifiable domains only (which makes sense from a data point of view), i'm already a very happy camper, as that includes a lot of STEM.

https://nitter.net/badlogicgames/status/2084008689044759022#m

Published: August 2, 2026 20:09

recommended reading. if we get "stuck" with improvements in verifiable domains only (which makes sense from a data point of view), i'm already a very happy camper, as that includes a lot of STEM. Ian Butler (@kinglycrow) Intelligence too spiky,…

R to @badlogicgames: addendum 3: jagged intelligence. watch the model do the most extraordinary hacking, then see it fall apart in another simple web project.

https://nitter.net/badlogicgames/status/2083665412332429567#m

Published: August 1, 2026 21:25

addendum 3: jagged intelligence. watch the model do the most extraordinary hacking, then see it fall apart in another simple web project.

R to @badlogicgames: addendum 2: kimi was able to do it, just faster. the cat's out of the bag. there is basically no way to rein this in. may we live in interesting times, something something.

https://nitter.net/badlogicgames/status/2083659421452767558#m

Published: August 1, 2026 21:01

addendum 2: kimi was able to do it, just faster. the cat's out of the bag. there is basically no way to rein this in. may we live in interesting times, something something.

24h later, gave into cybersec check of OAI, and i can only say i'm shocked at gpt 5.6 sol's capabilities. while kimi k3 was sufficient to break my DRM that's been undefeated for over 6 years (and many tried, ask me how i know :D), gpt 5.6 is on another level.

https://nitter.net/badlogicgames/status/2083653919461240895#m

Published: August 1, 2026 20:39

24h later, gave into cybersec check of OAI, and i can only say i'm shocked at gpt 5.6 sol's capabilities. while kimi k3 was sufficient to break my DRM that's been undefeated for over 6 years (and many tried, ask me how i know :D), gpt 5.6 is on another…

RT by @badlogicgames: I’ve been trying to tell this to anyone who would listen. routing is silly, only thing that reduces cost is context reduction through subagents. Trigger these through code, manage them as worker threads Context trees and workflows. No dials, pickers or routers

https://nitter.net/mattzcarey/status/2083356540849795388#m

Published: August 1, 2026 00:58

I’ve been trying to tell this to anyone who would listen. routing is silly, only thing that reduces cost is context reduction through subagents. Trigger these through code, manage them as worker threads Context trees and workflows. No dials, pickers or…

recommended reading. much more nuanced than the title makes it out to be. read till the end.

https://nitter.net/badlogicgames/status/2083331296869187994#m

Published: July 31, 2026 23:17

recommended reading. much more nuanced than the title makes it out to be. read till the end. Bilgin Ibryam (@bibryam) In defense of not understanding your codebase seangoedecke.com/in-defense-… Link In defense of not understanding your codebase …

recommended reading https://www.derekthompson.org/p/the-four-horsemen-of-the-ai-bubble

https://nitter.net/badlogicgames/status/2083305171577110677#m

Published: July 31, 2026 21:33

recommended reading derekthompson.org/p/the-four… Link The Four Horsemen of the AI Bubble Apocalypse The smartest reasons to worry about the state of AI in an age of intense volatility—and my best attempt to explain why each of those worries might be…

kv cache strikes again. https://manifest.build/blog/why-we-deprecated-our-llm-router/

https://nitter.net/badlogicgames/status/2083298132981346591#m

Published: July 31, 2026 21:05

kv cache strikes again. manifest.build/blog/why-we-d… Link Everyone is building LLM routers, we deprecated ours We don't believe in model routing anymore. For most use cases, sticking to a single battle-tested model is the best thing you can do.…

RT by @badlogicgames: Introducing Flue 2 — Build dynamic agents that evolve over time. Flue is a TypeScript framework for building the next generation of agents, powered by the @pidotdev agent harness. The Flue 1.0 Beta was released last month & has now been downloaded 700,000+ times. And from all of that feedback, we realized something we'd missed. Agents have a familiar problem: composability. How do you compose together different agent capabilities in a way that feels expressive AND maintainable, especially as you scale up complexity? Last week, I teased: “What if React for Agents?” and yes, as you will see, the inspiration here is obvious. But UI devs and agent devs have some things in common, including the same problem that the React team solved almost a decade ago with... Hooks! There are now things that you can do in Flue 2.0 with hooks that are just fundamentally difficult in other frameworks: A Flue agent can enforce a multi-step workflow, earn new tools once certain conditions are met, or trade up to a bigger model when the work gets too hard. Handling metadata and context no longer requires custom framework APIs and configuration. In Flue, you can pass data to a tool the same way you pass arguments to a function. I'm really excited for you to try Flue 2.0 out yourself. It's a big, bold take on what agents could be capable of in the future. Read more: https://flueframework.com/blog/flue-2/

https://nitter.net/FredKSchott/status/2083252640994275779#m

Published: July 31, 2026 18:05

Introducing Flue 2 — Build dynamic agents that evolve over time. Flue is a TypeScript framework for building the next generation of agents, powered by the @pidotdev agent harness. The Flue 1.0 Beta was released last month & has now been downloaded…

R to @badlogicgames: but the good news is that the same model can be used for both offensive and defensive work. on the defensive side, it helps reconstruct what might have happened tremendously. and once you have an idea how the incident happened, it's easier to create counter meassures and plug holes.

https://nitter.net/badlogicgames/status/2083248223553012021#m

Published: July 31, 2026 17:47

but the good news is that the same model can be used for both offensive and defensive work. on the defensive side, it helps reconstruct what might have happened tremendously. and once you have an idea how the incident happened, it's easier to create…

seriously, this is absolutely fucked. i'm kinda surprised not more shit is happening in cyber sec atm.

https://nitter.net/badlogicgames/status/2083247953540505998#m

Published: July 31, 2026 17:46

seriously, this is absolutely fucked. i'm kinda surprised not more shit is happening in cyber sec atm. Mario Zechner (@badlogicgames) komi k3 is fantastic at cracking DRMs. it's kinda scary. what would have taken weeks takes minutes now. (testing my own…

i assume they used vanilla pi, which is hilarious :D

https://nitter.net/badlogicgames/status/2083245249464295455#m

Published: July 31, 2026 17:35

i assume they used vanilla pi, which is hilarious :D Composio (@composio) We ran Kimi K3 through 3 more agent harnesses (Pi Agent, OpenCode, and Codex) bringing the comparison to 6 harnesses across 26 agentic tasks. 2 things stood out: Codex ranked…

here's a trick to get past lab filters. - start session with a model from another lab without filters - work with it for around 100k tokens - switch to the lab model 😬

https://nitter.net/badlogicgames/status/2083236361641808061#m

Published: July 31, 2026 17:00

here's a trick to get past lab filters. - start session with a model from another lab without filters - work with it for around 100k tokens - switch to the lab model 😬

RT by @badlogicgames: Weekend's coming, probably best (for your sanity) to take a break from vibecoding! Seems hard, but you want to go afk regardless? Using @badlogicgames 's Pi + tmux? pi-super lets you voice chat with your Pi sessions in tmux using GPT-Live (or just control them on mobile) ! Now v1.2.0 with an Android app (optional!) that lets you voice chat with screen locked / over your handsfree. https://github.com/pasky/pi-super

https://nitter.net/xpasky/status/2083233712351695156#m

Published: July 31, 2026 16:49

Weekend's coming, probably best (for your sanity) to take a break from vibecoding! Seems hard, but you want to go afk regardless? Using @badlogicgames 's Pi + tmux? pi-super lets you voice chat with your Pi sessions in tmux using GPT-Live (or just…

i gave the kids some new tools and now they are wrecking the house

https://nitter.net/badlogicgames/status/2083213695744610306#m

Published: July 31, 2026 15:30

i gave the kids some new tools and now they are wrecking the house Armin Ronacher ⇌ (@mitsuhiko) On the unreleased pi version you can go into settings and toggle on "fullscreen" mode. (or launch with --alt) Give all your exciting feedback here :P Video…

recommended viewing.

https://nitter.net/badlogicgames/status/2083208734612856997#m

Published: July 31, 2026 15:10

recommended viewing. Ben Davis (@davis7) My Opus 5 video is late, but that ended up being good because I would have made a very different video on release day I really like the idea of this model, but actually using it kinda sucks... Video —…

komi k3 is fantastic at cracking DRMs. it's kinda scary. what would have taken weeks takes minutes now. (testing my own DRM, not a "criminal")

https://nitter.net/badlogicgames/status/2083208426302152916#m

Published: July 31, 2026 15:09

komi k3 is fantastic at cracking DRMs. it's kinda scary. what would have taken weeks takes minutes now. (testing my own DRM, not a "criminal")

just realized: it's a shitty alt screen mode layout engine. back to true form!

https://nitter.net/badlogicgames/status/2083106157271384560#m

Published: July 31, 2026 08:23

just realized: it's a shitty alt screen mode layout engine. back to true form! Mario Zechner (@badlogicgames) welp, guess we have a layout engine now ... Video — https://nitter.net/badlogicgames/status/2083084598846644668#m

to each their own, but if this is where the timeline is headed, imma build myself one of those devices from the show Sliders and find me a new universe.

https://nitter.net/badlogicgames/status/2083105757529027050#m

Published: July 31, 2026 08:21

to each their own, but if this is where the timeline is headed, imma build myself one of those devices from the show Sliders and find me a new universe. Orchid (@orchid_hq) Introducing Orchid, the first assistant that actually gets you 🌸 Video …

working on JVM internals with sol makes the cyber security classifier go bonkers. jesus, i hate this. and no, i will not send my retina scans to persona or whoever does the verification that i'm a good boi.

https://nitter.net/badlogicgames/status/2083101990616227868#m

Published: July 31, 2026 08:06

working on JVM internals with sol makes the cyber security classifier go bonkers. jesus, i hate this. and no, i will not send my retina scans to persona or whoever does the verification that i'm a good boi.

RT by @badlogicgames: Let's talk a bit about what makes the Superlogical multiplexer different architecturally from traditional terminal multiplexers! There's a lot (a LOT) more coming, but wanted to share a little bit about the terminal-specific part compared to tmux and zellij.

https://nitter.net/mitchellh/status/2082936029426892960#m

Published: July 30, 2026 21:07

Let's talk a bit about what makes the Superlogical multiplexer different architecturally from traditional terminal multiplexers! There's a lot (a LOT) more coming, but wanted to share a little bit about the terminal-specific part compared to tmux and…

recommended reading. i agree with this message. internalize it.

https://nitter.net/badlogicgames/status/2082844396714704995#m

Published: July 30, 2026 15:02

recommended reading. i agree with this message. internalize it. Armin Ronacher ⇌ (@mitsuhiko) A post of ours on vendor lock in and LLMs. We don't like the growing trend of AI companies quietly hiding your data while stripping away your control. We think…

RT by @badlogicgames: Did you know you can run Pi from your phone? Pi runs on Android via Termux, a terminal emulator and Linux environment! Here’s Pi on mobile, spinning up a calendar reminder🗓️ We’ve loved seeing Pi run on phones, Raspberry Pi’s, IPads and more! Docs on how to try it out below.

https://nitter.net/pidotdev/status/2082814875105927243#m

Published: July 30, 2026 13:05

Did you know you can run Pi from your phone? Pi runs on Android via Termux, a terminal emulator and Linux environment! Here’s Pi on mobile, spinning up a calendar reminder🗓️ We’ve loved seeing Pi run on phones, Raspberry Pi’s, IPads and more! Docs on…