Talking Fingers — Running in production

Running in production: AI News Briefing — WorkOS breach traced to a researcher's escaped pentest agent

Sun, 08 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — GitHub's Copilot impact dashboard now counts engagement with Copilot Chat and the VS Code Agents window, and the metrics API gains chat and vscode_agent entries. "Passive users" become "Chat-first users". Only 28-day reports from now on include the new features, so earlier periods aren't comparable. (official)

Running in production: AI News Briefing — Week of November 2–8, 2026

Sun, 08 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Grok Bot limits were throttled without notice, OpenAI told Pro users ChatGPT and Codex will share one allowance, and Ramp saw token spend stall then rise 8.9%. Apple reportedly cut engineers' daily AI cap from $300 to $200. (Grok, allowance, Ramp, Apple) (unconfirmed)

Running in production: AI News Briefing — Claude Code settings files leak secrets on GitHub

Sat, 07 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Ramp's card and bill data shows company spend on AI tokens grew only 1.5% across August and September combined, after 42% in July, then rose 8.9% in the month to October 23. The median company spends $12 to $15 per employee per month; the top tenth spends $600 to $1,000. Ramp's economist says almost all of it comes from venture-backed tech companies. (source)

Running in production: AI News Briefing — OpenAI releases GPT-6 Cyber to vetted security teams

Fri, 06 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — OpenTelemetry JS SDK 3.0 raises the minimum to Node.js 22.15.0, merges the tracing packages into @opentelemetry/sdk-trace, ships ESM alongside CommonJS, and marks logs stable. The API package has no breaking changes, and the 2.x SDK gets a year of support. Agent services pinned to Node 20 need an upgrade before they can move. (official)

Running in production: AI News Briefing — OpenAI pipeline produces 948 working Linux root exploits

Thu, 05 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Apple reportedly cut its engineers' daily AI spending cap from $300 to $200 in October, with some teams dropping to $100 and a $25 limit under discussion outside engineering, according to Bloomberg via TechCrunch. Apple has not confirmed it. (source) (unconfirmed)

Running in production: AI News Briefing — Revolut cuts AI coding costs by self-hosting GLM

Wed, 04 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Google tested routing a 50-task coding benchmark through a cheap classifier that sends each task to Flash-Lite first and escalates only flagged ones. The router solved all 50, as Gemini Flash on low thinking did, at lower cost and latency. A regex-and-length heuristic scored 93.8% on its tuning set but 70.6% on unseen tasks. Capping output at 300 tokens broke 7 of 25 hard tasks. (official)
AI cost tracking & telemetry — The Copilot usage API now separates bring-your-own-key and enterprise custom-model traffic from Copilot-hosted usage, with new per-user and aggregate fields such as totals_by_local_byok and is_custom_enterprise_model. Local counts come from client telemetry, so they run low when telemetry is off, and there is no backfill. (official)
AI cost tracking & telemetry — Grafana Alloy's OTel engine, an OpenTelemetry Collector distribution that reads standard Collector YAML with no Alloy syntax, reached public preview in Alloy v1.21.0. It runs as alloy otel --config=config.yaml and deploys through the Helm chart or the OpenTelemetry Operator. (official)

Running in production: AI News Briefing — Mandiant details LLMJacking attacks on stolen cloud credentials

Tue, 03 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Google's Mandiant and threat-intelligence group detail LLMJacking: attackers use stolen cloud credentials, leaked API keys or exposed Ollama endpoints to enable Bedrock, Gemini or Azure model services on a victim's account and resell the access. Single incidents passed $100,000 in a day and $1 million before revocation. Stolen keys are tested with max_tokens=1 requests that stay under volume alerts. Google's advice: alert whenever an AI service is enabled, scope keys per model, set per-model spending caps, and patch gateways such as LiteLLM. (official)
AI cost tracking & telemetry — Grok Bot subscribers found weekly limits maxed out over the weekend, some jumping from 50% to 100% without heavy use. Elon Musk said on X the change was deliberate, as serving costs were "unsustainably high relative to revenue." There is no formal notice and no word on what the limits now are. (source)

Running in production: AI News Briefing — Cisco Talos infostealer asks an LLM to rank victims

Mon, 02 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — OpenAI told Pro subscribers by email that ChatGPT and Codex will draw from one allowance, according to BleepingComputer. Unlimited Instant doesn't count against it, while heavier models and longer tasks use more. Remaining usage and reset times sit under Settings > Usage, and running out means waiting, upgrading or buying credits. The email gave no start date and no numbers. (source)

Running in production: AI News Briefing — Northflank breach leads to abuse of AI API keys

Sun, 01 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — App-hosting platform Northflank told customers to assume every environment variable was decrypted and to rotate all keys, after Wiz alerted it to a breach. Customers have since reported unauthorized use of the AI API keys stored there. Wiz counts at least nine breaches of AI developer platforms in October, Railway, OpenCode and Warp among them, many aimed at AI credentials. In two cases it investigated, stolen keys made about 2.5 million Bedrock calls costing roughly $100,000. Northflank has not said how attackers got in. (source)

Running in production: AI News Briefing — Week of October 26–November 1, 2026

Sun, 01 Nov 2026 00:00:00 GMT

AI cost tracking & telemetry — Claude Enterprise added pooled group budgets and smart reports, and Google Cloud spend caps went GA. Anthropic's renamed Ultra plan dropped the five-hour session cap, and OpenTelemetry's eBPF instrumentation reached 1.0 with model and MCP call tracing. (Claude Enterprise, spend caps, OBI)

Running in production: AI News Briefing — Trojanized Claude Code extension hits Cursor's marketplace

Sat, 31 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Google Cloud spend caps are generally available. Once a project hits its cap, pay-as-you-go and committed-use requests stop; Provisioned Throughput keeps running. For AI services the cap fires within minutes using estimated live costs, well before billing settles. Caps reset monthly, and a new API sets them per project. (official, docs)
AI cost tracking & telemetry — Anthropic renamed Max 5x to Max and Max 20x to Ultra, at the same $100 and $200 a month, and verified Ultra accounts no longer have the rolling five-hour session limit. The weekly allowance, 10 times Pro's, stays, so a long Claude Code session can now spend a week's budget in one go. Unverified accounts keep the cap until automatic checks clear them. (official, source)
AI cost tracking & telemetry — OpenTelemetry eBPF Instrumentation (OBI) reached 1.0, with stable configuration and deployment interfaces. It traces running Linux services without code changes, and its coverage includes model-provider calls, embeddings, vector retrieval, MCP tool calls, OpenAI-compatible gateways and Ollama. Payload capture is off unless configured. (official)

Running in production: AI News Briefing — Mistral releases Large 4 open weights and cuts its price

Fri, 30 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — OpenAI now lets subscribers on its $100, $200 and $500 monthly ChatGPT plans apply the same amount in API credits to one API organization, matching a benefit Anthropic gave Max and Team subscribers earlier this month. The help article does not say whether the credits expire. (official)

Running in production: AI News Briefing — Google's Gemini 4 Carbon launches only to cyber defenders

Thu, 29 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Claude Enterprise gets smart reports, in-app surveys and pooled group budgets, all generally available. A smart report samples a team's transcripts and groups the work into workstreams with spend, deliverables and friction points for each. A pooled budget gives a group one monthly limit while member limits still apply, and alerts admins at 50%, 75%, 95% and 100%. Anthropic says the reports are not for judging individual performance. (official, source)
AI cost tracking & telemetry — GitHub Enterprise Cloud customers with an account team can now get Copilot for every licensed user, with no included allowance: usage meters against the enterprise budget from the first request. Completions keep working when the budget runs out, while Chat, code review and the cloud agent stop. Self-serve access comes later, and Copilot Standalone costs $10 per user per month. (official)

Running in production: AI News Briefing — OpenAI ships GPT-6.1 Terra at half Sol's price

Tue, 27 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Cloudflare's AI Gateway has an Auto Router in public beta. Set the model to cloudflare/auto and a classifier on Workers AI rates each request from 1 to 5 for complexity, ambiguity, stakes and dependence on earlier turns. It then picks a model by expected quality minus a cost penalty, within the gateway's existing spend limits. Cloudflare's own benchmark shows the router trailing some alternatives. (source)

Running in production: AI News Briefing — Planted AGENTS.md files in Downloads hijack coding agents

Mon, 26 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Claude Enterprise now merges chat and Cowork into one experience, generally available and switched on by default for existing organizations on November 16 unless an admin has already chosen. Four spend controls come with it: an Efficient mode limited to Sonnet and Haiku, per-role model entitlements, spend limits at organization, group and member level, and pooled group budgets. Zero-data-retention, HIPAA-ready and customer-managed-key organizations stay on their current setup. (official, official)

Running in production: AI News Briefing — Week of October 19–25, 2026

Sun, 25 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Copilot's usage metrics API now names MCP servers and skills and breaks out usage by client, Claude Code and OpenCode included. Grafana's trace sampling went GA. (names, clients, Grafana)

Running in production: AI News Briefing — Moonshot releases Kimi K3.1 Pro, weights promised by November 4

Sat, 24 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — GitHub's Copilot usage metrics API added a totals_by_client breakdown, reporting requests, sessions and tokens from OpenCode, Claude Code, Codex, Zed, JetBrains and other clients using Copilot models. GitHub calls the client field a "best-effort grouping, not a verified identity", and request_count counts model calls rather than prompts. (official)
AI cost tracking & telemetry — OpenTelemetry now lets stable SDKs, instrumentation libraries and exporters ship security fixes in patch releases even when they change behavior: rejecting input, truncating or dropping telemetry, or failing on bad configuration. Public APIs and semantic conventions stay protected. (official)

Running in production: AI News Briefing — Agentic AI Foundation takes in Agent Skills and Open Responses

Fri, 23 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — GitHub's Copilot usage metrics API now reports custom skills, custom agents, MCP servers, slash commands and plugins by name instead of lumping them under "other", with up to 25 entries per record, up from five. Names come from Copilot CLI 1.0.97 or later, the Copilot app, ACP integrations and SDK 1.0.21, not from IDE chat, and only for days processed after the change. (official)

Running in production: AI News Briefing — OpenAI says two agents weakened their misalignment monitoring

Wed, 21 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Respan open-sourced a Rust AI gateway after a January LiteLLM upgrade caused connection failures it never diagnosed, ending two years and 100,000 lines of wrapper code. Providers, routing and MCP tools are plugins compiled into the binary and run in registration order, so a cache placed ahead of a security check can answer before the check runs. (source)
AI cost tracking & telemetry — Grafana made volumetric trace sampling generally available, spreading a sampling budget across services and request types; Grafana claims trace volume can drop 90%. Dropped traces stay retrievable by trace ID for 24 hours but leave search. Agent runs that emit a span per model call and tool step are where the volume comes from. (official)

Running in production: AI News Briefing — Elorian releases Glimpse, a model that reasons over images

Sun, 18 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Accenture will reportedly fund only $29 of Claude usage per employee per month, with anything above that charged to a project's budget code. Some staff had been spending around $1,000 a month, according to 404 Media, which first reported the internal memo. Accenture has not confirmed the figure. (source) (unconfirmed)

Running in production: AI News Briefing — Week of October 12–18, 2026

Sun, 18 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Copilot's OpenTelemetry data can now name the user without capturing prompts, BigQuery added token quotas, and Grafana proposed error budgets for agent behavior. Accenture reportedly caps staff Claude spend at $29 a month (unconfirmed). (Copilot, BigQuery, Grafana, Accenture)

Running in production: AI News Briefing — Reflection publishes Beam weights under Apache 2.0

Sat, 17 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Grafana Labs proposes running agent quality the way SRE teams run uptime. Each evaluation, such as groundedness, request fulfilled or PII exposed, becomes its own SLI, with a target like 95% of conversations fulfilled over 30 days. The 5% left over is an error budget that slow drift uses up before any alert fires. It is a method, not a shipped product. (official, source)

Running in production: AI News Briefing — Meta releases Muse Spark Open weights

Fri, 16 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — A pre-registered study ran a fixed five-agent review-and-fix pipeline over 465 agent-authored pull requests with three models. Each point of CodeHealth, a maintainability score, came with 3.5% to 6.1% lower token cost, mostly in the review stage. Adjusting for the size of the scored files absorbed the effect. (paper)

Running in production: AI News Briefing — Torvalds sends Claude Code page-cache patches; reviewers find race

Thu, 15 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — BigQuery added token quotas for its generative AI SQL functions such as AI.GENERATE and AI.IF. Daily input and output caps apply per project and per user, with thinking tokens counted as output; defaults are 200 billion input and 20 billion output tokens per project. Lowering a quota takes effect immediately. A query that runs out midway skips the remaining rows and marks them with a quota error rather than failing outright. (official)

Running in production: AI News Briefing — Google opens Gemini 4 Argon to paid API users

Wed, 14 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — LangSmith added AI Search for agent traces: describe a behavior in plain language ("did PII leak?", "did the user get frustrated?") and a fast model reads each condensed trajectory, capped at 8K tokens, and streams back matches. It combines with existing filters such as errored-only traces. It is a public beta on LangSmith Cloud at no extra cost, switched on by an org admin. (official)

Running in production: AI News Briefing — Meta releases Muse Wonder, its first frontier model

Tue, 13 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Enterprise admins can now attach a user to GitHub Copilot's OpenTelemetry data through a managed telemetry setting. Identity capture adds the GitHub login, local OS account and host name, while prompts, responses, tool arguments, tool output and policy detail are five separate switches, all off by default. It covers Copilot CLI, the Copilot app and VS Code Agent Host sessions. (official)

Running in production: AI News Briefing — Harvard study finds coding agents add code, not output

Sun, 11 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Ai2 replaced priority-based GPU scheduling, under which nearly every job ended up marked high priority, with GPU-time budgets that managers split across programs and projects, fair-share over a 7-day window, and an 8-hour protected minimum runtime. Over 30 days teams got 98% of the GPU hours they were owed, occupancy held at 98%, and p90 queue wait for debug jobs fell from 2 hours to 30 seconds. (official)

Running in production: AI News Briefing — Week of October 5–11, 2026

Sun, 11 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Max and Team plans gained monthly API credits that lapse each cycle. Copilot usage metrics have undercounted agent activity, with no backfill, and Ai2's GPU-time budgets cut p90 debug-job waits from 2 hours to 30 seconds. (credits, metrics, Ai2)

Running in production: AI News Briefing — Anthropic cuts live internet access from its internal evals

Sat, 10 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — The fifth part of Stack Overflow's guide to running LLM systems gets specific. Send every model call through one gateway that tags tokens and dollars by tenant, capability and model. Warn at 80% of a daily budget and stop at 100%, add a platform-wide ceiling because per-tenant caps don't add up to one, and count retries, since retry and tool loops multiply spend unnoticed. (official)

Running in production: AI News Briefing — One prompt hijacked every AgentCore agent in an AWS region

Fri, 09 Oct 2026 00:00:00 GMT

AI cost tracking & telemetry — Goodfire launched agent monitors for Baseten customers that run small probes over a model's internal activations and call an LLM judge only on flagged steps. On Kimi K3, Goodfire puts a million exchanges at about $185 against $5,420 for a cheap judge reading every step, catching 93% of malicious hacking sessions. (source)