If you want to understand how fast AI is improving, look at intelligence per dollar. 1.5 years ago: o1 Pro: $150 / $600 per M tokens Today: GLM-5.3 Flash: $0.15 / $0.50 That’s a ~1000x collapse in price in under 1.5 years, while GLM-5.3 Flash is more intelligent than o1 Pro.

Jev is now in the AI SDK for Python. To test it, we ran two experiments: ▪︎ Detecting Python vs. English as text is typed ▪︎ Writing Python, one decision at a time 𝚞𝚟 𝚊𝚍𝚍 𝚊𝚒 vercel.com/blog/jev-for-pyth…

Apparently the biggest flex at the club in sf is a full Google Calendar

latam rtt is the real barrier: 140ms roundtrip to us-east kills the whole advantage of a 15ms decision model. dropping an inference node in são paulo puts local routing under 10ms for real-time messaging agents. devs here would run it non-stop

If you did something cool with Jev and codemode I want to know!

Got Jev? It's easier than you think!

CANCEL your weekend plans. You NEED to: • Replace fragile chat loops with Temporal state machines for crash-resilient agent workflows • Build a dynamic context assembler that strictly budgets tokens between memory, tools and docs per request • Implement a System-One router to handle 95% of triage in milliseconds, escalating only edge cases to reasoning models • Write a raw Model Context Protocol (MCP) server from scratch to expose your database securely to external agents • Build trajectory grading in CI that blocks PRs if an agent's tool-call sequence deviates from the golden path • Add an inter-agent sanitization proxy so Agent A's output can't execute a prompt injection on Agent B • Implement a cost kill-switch that halts any agent loop if projected token spend exceeds $0.50 per query • Build a 3-tier memory engine (Working, Episodic, Semantic) with automated eviction and compression policies • Set up KV-cache prefix sharing at the proxy layer to slash Time-To-First-Token by 80% for identical system prompts • Route 5% of production traffic to a new model silently, compare the trajectories and auto-generate a diff report • Build an API-to-Browser fallback where the agent spawns a headless browser if the REST API 404s • Automate a DPO pipeline: user thumbs-down → auto-format to preference pairs → queue a nightly LoRA fine-tune • Implement a PII unmasking proxy that swaps sensitive data for UUIDs before the LLM sees it and restores it post-generation • Set up a speculative decoding pipeline: local 2B model drafts tokens, cloud 70B verifies them, cutting latency 60% • Build a 4-tier graceful degradation chain: Frontier API → Mid-tier → Local Quantized → Semantic Cache • Add checkpointed human-in-the-loop approval gates wired directly into Slack for high-stakes agent actions • Trace every LLM hop with OpenTelemetry-style spans capturing exact token counts, latency and tool arguments • Fuzz your own multi-agent swarm with malformed tool outputs and context overflow to test self-healing recovery You have way too much to do. Bookmark & Repost.

I'm speedrunning my filesystem learnings. Turns out, brtfs cow-feature is GREAT for worktrees and terrible for sqlite. Next OC update knows that and - if you did sth silly like me - will migrate your database to a NOCOW spot.

Today at 2pm PT, @isaacbmiller1 and I will be walking through @DSPyOSS's Jev/System One implementation & the ReAnchor optimizer. Will also sharing some design patterns for for selective compaction, tool approvals, and subagent delegation using Jev. streamyard.com/watch/sbMTpJA…

“For you to see”?? See with Jev?! Multimodal confirmed??!!