Email Archive

Ollama session usage at 90%

Score 0.834 · Account tjphuhs@gmail.com · 4/12/2026, 4:52:29 PM

Ollama session usage at 90% from hello@ollama.com on 2026-04-12T20:52:29.000Z Hello tjphuhs, You've reached 90% of your session limit for your free plan. Your usage resets in in 4 hours, or you can upgrade your plan for higher limits: Upgrade Ollama [https://ollama.com/pricing] Just a as a heads up, you can view your usage at any time or disable these notifications here [https://ollama.com/settings]. If you have any questions, feel free to reach out. We’re here to help! – The Ollama Team

Ollama launch - one command to get up and running with Clawdbot, Claude Code, OpenCode, and Codex

Score 0.682 · Account tjphuhs@gmail.com · 1/27/2026, 10:13:46 AM

Ollama launch - one command to get up and running with Clawdbot, Claude Code, OpenCode, and Codex from hello@ollama.com on 2026-01-27T15:13:46.000Z https://ollama.com/download ollama launch is a new command that sets up and runs your favorite tools like Claude Code, Codex, OpenCode, Clawdbot, and Droid with local or cloud models. No environment variables or config files needed. Get Started Download Ollama 0.15.2+ [https://ollama.com/download], then download model(s) to run: GLM 4.7 Flash (~23GB

Ollama's Cloud models can now be used inside Claude Desktop

Score 0.648 · Account tjphuhs@gmail.com · 5/5/2026, 12:03:14 AM

Ollama's Cloud models can now be used inside Claude Desktop from hello@ollama.com on 2026-05-05T04:03:14.000Z Ollama 0.23 now supports Claude Desktop’s built-in third party inference. This allows all models from Ollama's Cloud to be available for use within Claude Cowork and Claude Code from Claude Desktop. https://docs.ollama.com/integrations/claude-desktop Get started Download Ollama 0.23 [https://ollama.com/download], then run: ollama launch claude-desktop You will be prompted to create an Ol

Ollama Pro annual plan

Score 0.628 · Account tjphuhs@gmail.com · 3/24/2026, 5:52:43 AM

Ollama Pro annual plan from hello@ollama.com on 2026-03-24T09:52:43.000Z https://ollama.com/upgrade?plan=pro&interval=year New Pro annual plan Ollama's Pro plan now has an annual option. For $200/year, you get 2 months free compared to the monthly plan. Upgrade to Pro annual [https://ollama.com/upgrade?plan=pro&interval=year] Ollama Pro and Max give you fast, reliable access to the newest open models like Nemotron-3-Super, Kimi-K2.5, MiniMax-M2.7, GLM-5, and GPT-OSS with built-in support for Ope

Qwen3-Coder-Next available in Ollama

Score 0.611 · Account tjphuhs@gmail.com · 2/6/2026, 9:35:49 AM

Qwen3-Coder-Next available in Ollama from hello@ollama.com on 2026-02-06T14:35:49.000Z https://ollama.com/library/qwen3-coder-next Qwen3-Next-Coder is now available on Ollama with version 0.15.5. This model supports a context window of 256K tokens and was trained specifically for agentic coding — tool use, long tasks, and recovering from errors. Download model [https://ollama.com/library/qwen3-coder-next] To get started, download Ollama [https://ollama.com/download] and run Qwen3-Coder-Next: oll

DeepSeek V4 Pro is now available on Ollama's cloud

Score 0.610 · Account tjphuhs@gmail.com · 4/28/2026, 5:07:42 AM

DeepSeek V4 Pro is now available on Ollama's cloud from hello@ollama.com on 2026-04-28T09:07:42.000Z https://ollama.com/library/deepseek-v4-pro DeepSeek-V4-Pro is now available to run on Ollama's cloud using the latest NVIDIA Blackwell hardware. https://ollama.com/library/deepseek-v4-pro Download Ollama [https://ollama.com/download] To use DeepSeek-V4-Pro with Claude Code [https://docs.ollama.com/integrations/claude-code], run: ollama launch claude --model deepseek-v4-pro:cloud For use with Open

Ollama launch Pi: the coding agent behind OpenClaw

Score 0.597 · Account tjphuhs@gmail.com · 3/30/2026, 7:50:11 AM

Ollama launch Pi: the coding agent behind OpenClaw from hello@ollama.com on 2026-03-30T11:50:11.000Z https://docs.ollama.com/integrations/pi Ollama can now launch Pi [https://pi.dev/], the coding agent that powers OpenClaw. Pi is designed to be a minimal coding harness that can be adapted to your workflows to create your own coding agent. Pi comes bundled with powerful primitives to build on, and can be extended with extensions [https://pi.dev/packages], skills, prompt templates, and themes. Get

MiniMax-M2.7 with self-improvement & research in OpenClaw

Score 0.591 · Account tjphuhs@gmail.com · 3/19/2026, 5:54:03 AM

MiniMax-M2.7 with self-improvement & research in OpenClaw from hello@ollama.com on 2026-03-19T09:54:03.000Z MiniMax-M2.7 is now available to run via Ollama's cloud. This new model is designed to excel at completing end-to-end tasks in software engineering and office productivity while improving its character and emotional intelligence. M2.7 is also good at self-improvement using data from the web. This allows assistants like OpenClaw to do research and learn new skills. To get started, download

API usage has reached your notification threshold

Score 0.572 · Account tjphuhs@gmail.com · 3/24/2026, 1:09:29 PM

API usage has reached your notification threshold from billing@tm1.openai.com on 2026-03-24T17:09:29.000Z API usage has reached your notification threshold Hi there, Your API usage this month for Personal (org-2Qznefmo9zbO38wb70oBsobM) has reached the alert configured for 100.00% ($120.00) of your $120.00 budget for this month. Manage usage alerts Best, The OpenAI team You received this email because you have a paid account with OpenAI If you have any questions please contact us through our help

API usage has reached your notification threshold

Score 0.571 · Account tjphuhs@gmail.com · 3/24/2026, 4:13:08 AM

API usage has reached your notification threshold from billing@tm1.openai.com on 2026-03-24T08:13:08.000Z API usage has reached your notification threshold Hi there, Your API usage this month for Personal (org-2Qznefmo9zbO38wb70oBsobM) has reached the alert configured for 80.00% ($96.00) of your $120.00 budget for this month. Manage usage alerts Best, The OpenAI team You received this email because you have a paid account with OpenAI If you have any questions please contact us through our help c

API usage has reached your notification threshold

Score 0.570 · Account tjphuhs@gmail.com · 3/24/2026, 1:25:30 PM

API usage has reached your notification threshold from billing@tm1.openai.com on 2026-03-24T17:25:30.000Z API usage has reached your notification threshold Hi there, Your API usage this month for Personal (org-2Qznefmo9zbO38wb70oBsobM) has reached the alert configured for 80.00% ($120.00) of your $150.00 budget for this month. Manage usage alerts Best, The OpenAI team You received this email because you have a paid account with OpenAI If you have any questions please contact us through our help

Fwd: MiniMax-M2.7 with self-improvement & research in OpenClaw

Score 0.565 · Account oc.tjphuhs@gmail.com · 3/19/2026, 8:38:32 AM

Fwd: MiniMax-M2.7 with self-improvement & research in OpenClaw from tjphuhs@gmail.com on 2026-03-19T12:38:32.000Z ---------- Forwarded message ---------- From: Ollama <hello@ollama.com> Date: Mar 19, 2026 at 5:54 AM -0400 To: tjphuhs@gmail.com Subject: MiniMax-M2.7 with self-improvement & research in OpenClaw > > > MiniMax-M2.7 is now available to run via Ollama's cloud. This new model is designed to excel at completing end-to-end tasks in software engineering and office productivity while impro

Fwd: MiniMax-M2.7 with self-improvement & research in OpenClaw

Score 0.565 · Account tjphuhs@gmail.com · 3/19/2026, 8:38:32 AM

Fwd: MiniMax-M2.7 with self-improvement & research in OpenClaw from tjphuhs@gmail.com on 2026-03-19T12:38:32.000Z ---------- Forwarded message ---------- From: Ollama <hello@ollama.com> Date: Mar 19, 2026 at 5:54 AM -0400 To: tjphuhs@gmail.com Subject: MiniMax-M2.7 with self-improvement & research in OpenClaw > > > MiniMax-M2.7 is now available to run via Ollama's cloud. This new model is designed to excel at completing end-to-end tasks in software engineering and office productivity while impro

Your API usage limits have increased

Score 0.563 · Account tjphuhs@gmail.com · 4/24/2026, 10:37:56 PM

Your API usage limits have increased from noreply@tm.openai.com on 2026-04-25T02:37:56.000Z Your API usage limits have increased Review your new rate limits in your account settings. Hi there, We're happy to share that we've automatically moved your organization from Usage Tier 3 to Usage Tier 4 based on your usage history on our platform. For most organizations, this comes with an increase in rate limits across several models. You can review your new usage tier and limits in your account settin

High Performance Rate Limiting at Databricks

Score 0.548 · Account tjphuhs@gmail.com · 5/13/2026, 11:30:35 AM

High Performance Rate Limiting at Databricks from bytebytego@substack.com on 2026-05-13T15:30:35.000Z rollout are worth noting. The team built a localhost sidecar next to the Envoy ingress to host the batch-reporting logic, because Envoy is third-party code they could not change directly. Before in-memory counting was ready, a Lua script on Redis batched writes together to keep batch-reporting latency manageable during the migration. The rebuild reframes what rate limiting is as a system problem

High Performance Rate Limiting at Databricks

Score 0.525 · Account tjphuhs@gmail.com · 5/13/2026, 11:30:35 AM

High Performance Rate Limiting at Databricks from bytebytego@substack.com on 2026-05-13T15:30:35.000Z of its own. Between the moment a client starts exceeding a limit and the moment the server tells it to reject, traffic can leak through. A hundred milliseconds of overshoot at high QPS amounts to a lot of requests. The team wanted guarantees that kept overshoot within roughly 5 percent of the policy, and reaching that target required three-layered fixes. The first was a rejection rate returned b

High Performance Rate Limiting at Databricks

Score 0.525 · Account tjphuhs@gmail.com · 5/13/2026, 11:30:35 AM

High Performance Rate Limiting at Databricks from bytebytego@substack.com on 2026-05-13T15:30:35.000Z for a second, durable storage is more than the problem requires. The count can live in memory on the server that owns it, and losing that server during a restart costs almost nothing. The challenge is that a single server cannot hold counts for every rate limit key across the fleet. The service needs a way to partition keys across servers, and a way for any client to quickly find the server that

Fwd: When Ozempic stops working (and what 10% of users already know)

Score 0.524 · Account tjphuhs@gmail.com · 3/17/2026, 2:05:41 PM

Fwd: When Ozempic stops working (and what 10% of users already know) from tjphuhs@gmail.com on 2026-03-17T18:05:41.000Z TJ Begin forwarded message: From: Seed Oil Scout <newsletter@seedoilscout.com> Date: March 17, 2026 at 1:36:08 PM EDT To: tjphuhs@gmail.com Subject: When Ozempic stops working (and what 10% of users already know) 96 The non-responder problem, the plateau trap, and the side effects pharma buries in the fine print. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏

Bryan Johnson’s adaptogen protocol

Score 0.521 · Account tjphuhs@gmail.com · 3/20/2026, 4:02:31 PM

Bryan Johnson’s adaptogen protocol from hello@bryanjohnson.com on 2026-03-20T20:02:31.000Z [Ashwagandha + Rhodiola support stress response, cognitive function and a balanced mood](https://blueprint.bryanjohnson.com/collections/ashwagandha-rhodiola) How to get ashwagandha and rhodiola You can supplement these adaptogens. We’ve combined ashwagandha and rhodiola into 1 daily capsule. In 1 capsule, you’ll get: - + 120mg of ashwagandha + 300mg of rhodiola Combining ashwagandha and rhodiola means you

High Performance Rate Limiting at Databricks

Score 0.518 · Account tjphuhs@gmail.com · 5/13/2026, 11:30:35 AM

High Performance Rate Limiting at Databricks from bytebytego@substack.com on 2026-05-13T15:30:35.000Z team asked a harder question. Does every request truly need to wait for a rate limit decision before proceeding? They considered three alternatives: The first was prefetching tokens on the client, where the client pulls a block of capacity and answers rate limit checks locally. The second was batching requests on the client and waiting for a response before releasing them. The third was sampling

Do Semax and Selank Need to Be Cycled?

Score 0.517 · Account tjphuhs@gmail.com · 3/19/2026, 2:13:47 PM

Do Semax and Selank Need to Be Cycled? from derekpruski@substack.com on 2026-03-19T18:13:47.000Z Option 1 — Defined cycles with a break Run a 4–8 week research protocol, then take 2–4 weeks off. This is the better approach for longer, higher-frequency protocols. Because of the BDNF-driven building effect, many researchers note that cognitive and mood benefits in RS persist well into the off period — the washout isn’t a cliff, it’s a gradual fade. You’re not losing everything the moment the proto

Anthropic just pissed on our Cheerios (here's the fix)

Score 0.514 · Account tjphuhs@gmail.com · 4/8/2026, 9:27:10 PM

Anthropic just pissed on our Cheerios (here's the fix) from hello@effortlessaiautomation.com on 2026-04-09T01:27:10.000Z I burned $245 in 2 days. Here's what I changed. Yoooo T.J. this is pretty lame but.... About 4 days ago Anthropic banned OAuth for third-party tools like OpenClaw. I burned through $245 in 2 days trying to compensate. Not great. So I rebuilt my entire AI model stack from scratch, and honestly the new setup is way more powerful than before. In my latest video I show you exactly

High Performance Rate Limiting at Databricks

Score 0.514 · Account tjphuhs@gmail.com · 5/13/2026, 11:30:35 AM

High Performance Rate Limiting at Databricks from bytebytego@substack.com on 2026-05-13T15:30:35.000Z earlier rejection rate mechanism became unnecessary, and the team eventually converted every rate limit in the system to a token bucket. Three Coupled Decisions The Databricks story resolves into three decisions that depend on each other: The first is the algorithm, which determines how the counter behaves at the boundaries of time intervals. Fixed window, sliding window, and token bucket each p

How Figma Upgraded Data Pipeline from Multi-Day Latency to Real-Time

Score 0.512 · Account tjphuhs@gmail.com · 5/12/2026, 11:31:03 AM

How Figma Upgraded Data Pipeline from Multi-Day Latency to Real-Time from bytebytego@substack.com on 2026-05-12T15:31:03.000Z is based on publicly shared details from the Figma Engineering Team. Please comment if you notice any inaccuracies. When SELECT * Becomes Your Bottleneck Figma’s original data pipeline did what’s called a full sync. Every run copied the entire contents of a database table, regardless of how much had actually changed since the last run. If a table had ten million rows and

When Ozempic stops working (and what 10% of users already know)

Score 0.511 · Account tjphuhs@gmail.com · 3/17/2026, 1:36:07 PM

When Ozempic stops working (and what 10% of users already know) from newsletter@seedoilscout.com on 2026-03-17T17:36:07.000Z The non-responder problem, the plateau trap, and the side effects pharma buries in the fine print. ****************************************************************** When Ozempic Stops Working: The 1-in-10 Problem Nobody Talks About ****************************************************************** ( https://eatprima.com/discount/SOS15 ) PRIMA ( https://eatprima.com/discou