I've published a new, general-purpose terminal specification that gives any program a way to tell the terminal what it's doing: idle, working, waiting, finished, or failed, and why. It is easy to implement on both sides. I've written more about why: The problem this solves is generic and applies in compelling ways to all sorts of use cases (e.g. package managers, build tools), but it really rears a hideous head when it comes to AI and the "agentic inbox" problem. I found over 250 different agent orchestrators (with various goals) that all individually implement a heuristic based approach to detecting whether things like Claude Code are working, blocked, done, etc. If you look at @herdrdev's commit history, you can see around 10 compatibility changes to detect Claude Code within just the past 3 months. (This isn't a dig at Herdr! They're doing great work with what they have, and everyone else is doing the same thing). Heuristics are not the way. And over-indexing on agentic use cases isn't the way, because this problem is really interesting for other tools too: Homebrew, Terraform, Cargo, etc. etc. Proprietary protocols and out of band APIs are not the way. They have an O(N) integration problem and require extra work to work over SSH or within local VMs/containers. The program status specification (OSC 7501) solves this in a reliable, deterministic way that is general-purpose and can be easily adopted by the entire industry. Read more:

First PSSR came to PS5 Pro. Now Quick Spectral Super Resolution (QSSR) is coming to PS5. Details on new upscaling tech, coming first to Marvel’s Wolverine and Ghost of Yōtei:

astra is running a loop where its checking my battery and making sure I have enough charge on my laptop... it stops if the batter drops below 5% cause it might have builds running which would get cancelled??

I can’t stress enough how little an idea matters compared to the agency of the people executing the idea. I have had the privilege of knowing and sometimes even working with some of the most successful people (by various metrics). The difference between mediocre and excellent work and outcomes is predominantly one of agency. In practice this means: they dont wait for things to happen to them they go out and make things happen for them. They don’t wait for someone else to do something, for someone to teach them, for someone to give them the path, etc. They just go out and find a way to do it. I think the single biggest superpower these people have is the realization/belief that the world around them is completely mutable. Most everything that happens is because a person made it happen. I used to tell people to look around the room you’re sitting in. Look at everything. Every noun. It almost all exists because a person willed it into existence. Nothing is stopping you from doing the same. I see people online all the time dismissing someone else’s success because “I had that idea first” or whatever. I mean… yeah? If so then the difference is… you. So a bit of a self own whenever I hear that. Number one tip: act with agency.

If the same general agent can understand a car, an arm, a humanoid, etc. through their sensor/action interfaces, you start to decouple intelligence from the hardware platform itself. “LLM as puppeteer” is probably just the beginning. The bigger shift might be robots converging on an abstraction layer where a general agent can express intent without needing to understand the low-level control details of every embodiment. Almost like a hardware abstraction layer for physical intelligence.

is astra inference okay? so many missing whitespaces in text, mangled text in general. it is mentioned in their model guidance docs (subagent communication section), but still interesting to see it happen with the main agent <> human channel as well

somedays you just need to look at graphs very very carefully and audit your agent's work and the results can be so shockingly good; a system which was failing on its head now has a lot more scaling capability

we open-sourced the full Grok Build app for anyone to take a look at the code :) you can see all parts of how the agent loop runs, how the terminal rendering works, compaction, goals, subagents and more

SpaceXAI’s Grok 4.5 scores 54 to place fourth on the Artificial Analysis Intelligence Index following only Fable 5, GPT-5.5, and Opus 4.8. It scores on par with GPT-5.5 in Codex on the Artificial Analysis Coding Agent Index in the Grok Build harness, at much lower cost Grok 4.5 improves 16 points over Grok 4.3 on the Intelligence Index, bringing SpaceXAI to the intelligence frontier behind only OpenAI and Anthropic, and outperforming all open weights models and notably Google’s Gemini models. Key standout areas of performance are agentic knowledge work and coding. Grok 4.5 in Grok Build scores 76 on the Artificial Analysis Coding Agent Index, on par with GPT-5.5 (xhigh) in Codex and just below Fable 5 (max) in Claude Code, and at a small fraction of the token usage and price. Congratulations to @SpaceXAI, @cursor_ai, and @elonmusk on the impressive release! Key Takeaways: ➤ Grok 4.5 performs very strongly on agentic tasks. Grok 4.5 ranks #4# on GDPval-AA v2 with an Elo of 1543, between Claude Opus 4.8 (1600) and GLM-5.2 (1513). It achieves the top score on 𝜏³-Banking of 33%, above 31% from GPT-5.5 (xhigh), and sits on the cost vs performance Pareto frontier across all three agentic evaluations in the Intelligence Index ➤ Grok 4.5 is one of the most cost efficient models to run for near-frontier intelligence. It costs $0.31 per task on the Artificial Analysis Intelligence Index and $2.59 per task on the Artificial Analysis Coding Agent Index within Grok Build ➤ Low cost for Grok 4.5 is driven by both low pricing and token efficiency. Grok 4.5 has a headline price over 60% lower than Claude Opus 4.8 and GPT-5.5, and used ~14k output tokens per Intelligence Index Task - over 60% lower than Opus 4.8. On the Coding Agent Index, Grok 4.5 stands out on the Pareto frontier of Coding Agent Index score vs. Total Tokens, using only 1.9M tokens for the Coding Agent Index while scoring 76 ➤ As a coding agent, Grok 4.5 in Grok Build is on par with GPT-5.5 and offers efficiency benefits: In our Artificial Intelligence Coding Agent Index that consists of DeepSWE, Terminal-Bench v2, and SWE-Atlas QnA, Grok 4.5 in Grok Build ranks third, on par with GPT-5.5 (Codex) and below Fable 5 (Claude Code). It is also very efficient in achieving this result: Grok 4.5 in Grok Build cost $2.49 per task while Fable 5 in Claude Code cost $11.80 and GPT-5.5 in Codex $5.07. This is driven by relatively low token pricing and the model using far fewer tokens than comparable models (1.9M average tokens used per task), significantly less than Fable 5 in Claude Code (7.2M) and GPT-5.5 in Codex (6.2M) Other model details: ➤ Context window of 500k tokens - a reduction from Grok 4.3’s 1M token context, but retaining configurable reasoning and vision input ➤ Pricing of $2/$6 per 1M tokens of input/output; cache hits are discounted by 75% to $0.5 per 1M tokens, and costs still double with long (>200k token) inputs ➤ As Elon Musk has disclosed, Grok 4.5 is 3x larger than its predecessor at 1.5T parameters

Bug fixes shipping to Grok Build 0.2.20 (release notes will be available in the TUI and on change-log website) • Eliminate ghost-cell artifacts in markdown table rendering • Make monitors visible and killable to the model • Preserve soft breaks in plan preview • Add image_to_video and reference_to_video tools • Add bundled imagine skill • Convert ICO images to PNG • Resolve [Image # N] attachment references in image_edit • Open fullscreen viewer on Enter for Search and ListDir blocks • Route MCP lifecycle notifications by sessionId + bound per-server init • Route mouse-wheel scroll to /btw overlay panel • Compaction: neutralize echoed summarization instruction in summary seed • Structured compaction prompt (successor-assistant, carry-forward, block) • Dedupe between-turn subagent completion reminders • Allow auto-update to downgrade on rollback • Dedupe MCP servers declared in both .mcp.json and plugin.json • Fix local stdio MCP servers on Windows

Bug fixes shipping to Grok Build 0.2.8 (release notes will be available in the TUI and on our website!) - support interject action for queued prompts - restore prompt focus on terminal tab click/FocusGained - highlight commands in inline ghost and multi-line prompts - reject <8×8 images on client - windows – force static CRT linking on to fix ARM64 DLL_NOT_FOUND - fix dim terminal when /rewind menu open - mouse-click support for cancel-turn and /rewind - append transcript path to compaction summary - fix stale 5-min default in monitor timeout_ms prompting - cleaned up the system-prompt more for task adherence

Bug fixes shipping to Grok Build 0.2.7 (release notes will be available in the TUI) • Wrap around on Up/Down in slash menu and history search • Restore subagent UI and replay on session resume • Fix Ctrl+Delete on windows • Windows drag-and-drop screenshot images + Ctrl/Alt+V image input • Add Windows-friendly alternatives for Ctrl+Enter / Ctrl+; • Strip base64 str images from read_file tool calls & pass as multimodal vision tokens • Share terminal backend, scheduler, monitor across subagent sessions • Image pipeline improvements (fix truncation, min pixels) • /login command to reauth from inside TUI • Add /usage • Handle Cmd+A in prompt to select all text in ghostty

Bug fixes shipping to Grok Build 0.2.3 (release notes will be available in the TUI) - add “Yes, and don't ask again for anything (always-approve mode)" - add alpha/stable to welcome screen - JetBrains/JediTerm terminal detection so TUI does not get confused and detect it as some other terminal - persist model ID instead of display name for default_model - clamp Q&A height to prevent ratatui buffer overflow - better UX for tmux inside ssh copy-paste issues - store vim mode persistently in the config.toml to prevent restart loss - memory usage improvements for managing chat history on the hot path