Backburner splits a 27-billion-parameter language model between a MacBook Pro and iPhone connected via USB-C, achieving 29-44% faster inference on long contexts by distributing computation across both devices' GPUs. The system maintains identical outputs to running the model on the Mac alone while supporting up to 196k tokens of context on an iPhone 17 Pro Max.

• Split prefill workload: Mac runs layers 1-40 while iPhone runs layers 41-64 in parallel, with the iPhone holding older KV cache pages past 64k context and computing attention over them during both prefill and decoding.
• Measured performance gains: 44% faster throughput at 16k context (157 vs 109 tok/s), and ability to maintain 8-bit precision at 128k tokens versus the Mac alone dropping to 4-bit to fit in memory.
• Greedy decoding is token-identical between Mac-only and Mac+iPhone configurations across tested context lengths (8k, 32k, 140k), confirming the split computation produces correct results.

DeepSeek V4.1 Flash is a 552B-parameter mixture-of-experts model that activates only 8B-16B parameters per token and supports a 1M-token context window for handling long documents and agentic workloads. The model cuts KV-cache memory usage by 4x compared to its predecessor while improving coding, reasoning, and agent performance.

• Activates just 8B parameters during input processing and 16B during generation, making it efficient despite the massive 552B backbone
• Reduces memory footprint by roughly 4x versus DeepSeek-V4-Flash-0731 through Compressed Sparse Attention 2 and a Causal Encoder-Decoder architecture
• Offers configurable reasoning-effort levels so developers can adjust latency and cost versus reasoning depth
• Handles multimodal input (text and images) natively with a 1M-token context window, designed for agents processing large amounts of data

Tencent released Hy4 preview, a large language model with 770B parameters and over 1M token context window, designed for coding, office work, and scientific research. The model outperformed competitors like GLM-5.3 and Kimi K3 in Tencent's internal evaluation and can be accessed free for two weeks through WorkBuddy and CodeBuddy.

• Hy4 preview scored 2.99/4.00 in Tencent's blind evaluation of 203 engineering tasks, beating GLM-5.3 (2.92) and Kimi K3 (2.94)
• The model participated in its own development, autonomously optimizing training methods and inference infrastructure, increasing throughput by 31.8% over baseline
• Pricing is competitive at $0.834 per million input tokens and $2.501 per million output tokens, with specialized optimization for game development and scientific research tasks

Simon Willison runs Claude Fable 5 through its paces, finding it slower and pricier than Opus 4.8 but far more knowledgeable thanks to its 1 million-token context. He tests it on real-world coding tasks—upgrading a MicroPython sandbox to full CPython in WASM and adding pause-resume hooks to Datasette Agent—showing it can build complex features end-to-end.

• Fable 5 costs twice as much as Opus 4.5–4.8 ($10/$50 per million tokens vs their pricing) and runs slower, but handles every complex prompt thrown at it.
• Its 1M-token context gives it dramatically deeper recall than Opus 4.8—listing a dozen detailed open-source projects with dates versus Opus's brief list of four.
• It successfully converted a MicroPython-wasm project to full CPython in WASM, ultimately producing a working 13.9 MB wheel runnable via uv, demonstrating real end-to-end coding capability.

This article shows that SKILL.md files aren’t static prompts but loader specifications defining what to load, when, and at what cost. It breaks down the three progressive-disclosure levels, explains how architecture—not instruction content—drives context consumption, and highlights common antipatterns that bloat or break skills.

• A 1,200-line monolithic SKILL.md ate 20% of the context window every turn; splitting it into a 180-line driver plus reference files and a script dropped that to 7%.
• SKILL.md files are loader specs with three tiers—frontmatter (~100 tokens, always loaded), body (loads on invocation, keep under 500 lines), and references/scripts (loaded or run only on demand).
• Adding YAML frontmatter to reference files accidentally promotes them to always-loaded skills, cluttering the skill list and causing out-of-context invocations—removing it fixed silent routing errors.
• Context consumption is driven by how content is architected across these layers, not by how much instructional detail is written.

This tweet notes that while CLAUDE.md solves the instruction-handling side, you still need to track your model’s context budget. It links to Headroom, a simple one-line-install status bar that shows your current context usage percentage in your editor’s status line.

• Structuring prompts in a defined markdown file (CLAUDE.md) with sections for goals, context, constraints, and examples reduces ambiguity and improves model reliability
• Headroom is a one-line-install status bar tool that displays real-time context window usage percentage directly in the editor's statusline
• Combining CLAUDE.md and headroom addresses two separate problems: instruction clarity and token budget tracking, preventing unexpected conversation truncation

Anthropic reduced Claude Code’s prompt cache TTL from one hour to five minutes, causing higher token write costs and faster quota depletion for long coding sessions. Developers report frequent cache misses—especially with large context windows—hitting usage limits and degrading performance. Anthropic says it will tweak default context windows but won’t offer a global TTL setting.

• Anthropic quietly cut Claude Code's cache TTL from one hour to five minutes in early March, causing far more expensive cache misses on long sessions.
• Cache writes cost 25% more per token than hits, so Pro users ($20/mo) report exhausting quotas after just two prompts in five hours.
• Anthropic says TTL is auto-selected client-side with no global override, but is testing a smaller 400K default context window (up to 1M optional) to curb costs.
• Beyond cost, users report degraded model behavior—looping, repetition, and "overthinking"—since a late-March update, separate from the caching issue.

PostHog AI has evolved significantly over its first year, transforming from a basic tool to a comprehensive AI agent capable of complex data analysis and task execution. Key learnings highlight the importance of model improvements, context, and user trust in AI interactions. The platform is now utilized by thousands weekly, offering insights into product usage and error management.

• PostHog AI went from a basic chatbot to an agent handling complex data analysis and task execution over one year, now used by thousands weekly
• Model improvements alone drove significant capability jumps, but context (giving the agent access to the right data/docs) mattered just as much as raw model quality
• User trust had to be earned incrementally—showing reasoning steps, sources, and letting users verify/correct outputs was key to adoption
• Error handling and graceful failure recovery became a major engineering focus as the agent took on more autonomous, multi-step tasks