Hacker News: kflansburg

New comment by kflansburg in "Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)"

kflansburg — Tue, 27 Oct 2026 02:01:18 +0000

At no point do we claim that it is a bug with the model. We specifically outline how it was a mis-configuration on Cloudflare's part and a bug in SGLang. We name the model in the title because our customers need to know which of our endpoints was affected. In fact, we say "the GLM-5.3 Workers AI model", not "GLM-5.3".

New comment by kflansburg in "Clef: Open-source decision models, and new RL fine-tuning platform"

kflansburg — Thu, 01 Oct 2026 17:11:01 +0000

> Our post-training utilizes label-smoothed cross-entropy for valid schema outputs paired with a Brier loss to refine probability calibration.

New comment by kflansburg in "Kev – A Jev-Compatible API on top of DiffusionGemma running on Workers AI"

kflansburg — Sat, 19 Sep 2026 01:52:40 +0000

Some users on X [1] were discussing the use of DiffusionGemma for Jev-like use cases. Similar to Jev, diffusion models generate output fully in parallel. We achieve similar estimation of relative confidence by looking at token log probabilities. Finally, by disabling reasoning we achieve low output tokens and similar latencies. This demo lets you compare the output to Jev for some canned prompts, or see the DiffusionGemma output for your own prompts.

[1] Original X post with vLLM PR https://x.com/mmastrac/status/2100626193943052784

Kev – A Jev-Compatible API on top of DiffusionGemma running on Workers AI

kflansburg — Sat, 19 Sep 2026 01:52:40 +0000

Article URL: https://kev.workers-ai-mle.workers.dev/

Comments URL: https://news.ycombinator.com/item?id=49762547

Points: 5

# Comments: 1

New comment by kflansburg in "OpenRouter raises $113M Series B"

kflansburg — Sun, 31 May 2026 04:03:45 +0000

My point was not about our ranking specifically, but the methodology of taking a point-in-time sample.

New comment by kflansburg in "OpenRouter raises $113M Series B"

kflansburg — Sat, 30 May 2026 20:46:06 +0000

I would recommend tracking this data over time. I work on Cloudflare's KV cache for Kimi K2.6, and while there are periods where our cache rate is low, we are frequently in the 80-90% range. OpenRouter shows us at 87.3% at the time of this post. We observe cache rates change quite a bit from hour to hour.

New comment by kflansburg in "Making deep learning go brrrr from first principles (2022)"

kflansburg — Sat, 23 May 2026 13:20:30 +0000

If you aren't already aware, Karpathy has several videos that could get you there in a few hours https://www.youtube.com/@AndrejKarpathy

New comment by kflansburg in "Ask HN: Who is hiring? (May 2026)"

kflansburg — Fri, 01 May 2026 17:06:58 +0000

Cloudflare | Systems or ML Engineer, Workers AI | Austin, TX or London, UK or San Francisco, CA (Hybrid) | Full-Time | https://cloudflare.com

Cloudflare is building across the entire AI stack. Here are some exciting things that we have launched recently:

- Kimi k2.5: https://blog.cloudflare.com/workers-ai-large-models/

- Kimi Performance Improvements: https://blog.cloudflare.com/high-performance-llms/

- Kimi k2.6 Speculative Decoding and Shared KV Cache: https://x.com/kevin_flansburg/status/2050238819065299110

- Unweight Tensor Compression: https://blog.cloudflare.com/unweight-tensor-compression/

- Code Mode MCP Servers: https://blog.cloudflare.com/code-mode/

- Agents SDK: https://blog.cloudflare.com/building-agents-with-openai-and-...

- Agent Memory: https://blog.cloudflare.com/introducing-agent-memory/

- Internal AI Tooling: https://blog.cloudflare.com/internal-ai-engineering-stack/

- Release Cog v0.19: https://github.com/replicate/cog/releases/tag/v0.19.0

- Dynamic Worker Sandboxes: https://blog.cloudflare.com/dynamic-workers/

- Dynamic Workflows: https://blog.cloudflare.com/dynamic-workflows/

We are looking for systems and ML engineers to help build our edge inference platform:

- Senior Systems Engineer, Workers AI - https://job-boards.greenhouse.io/cloudflare/jobs/7764827?gh_...

- Senior / Principal Machine Learning Engineer, Workers AI- https://job-boards.greenhouse.io/cloudflare/jobs/6297179?gh_...

New comment by kflansburg in "Ask HN: Who is hiring? (April 2026)"

kflansburg — Wed, 01 Apr 2026 17:30:33 +0000

Cloudflare | Systems or ML Engineer, Workers AI | Austin, TX or London, UK or San Francisco, CA (Hybrid) | Full-Time | https://cloudflare.com

Cloudflare is building across the entire AI stack. Here are some exciting things that we have launched recently:

- Release Cog v0.17: https://github.com/replicate/cog/releases/tag/v0.17.0

- Dynamic Worker Sandboxes: https://blog.cloudflare.com/dynamic-workers/

- Kimi K2.5: https://blog.cloudflare.com/workers-ai-large-models/

- Code Mode MCP Servers: https://blog.cloudflare.com/code-mode/

- Agents SDK: https://blog.cloudflare.com/building-agents-with-openai-and-...

We are looking for systems and ML engineers to help build our edge inference platform:

- Senior Systems Engineer, Workers AI - https://job-boards.greenhouse.io/cloudflare/jobs/7764827?gh_...

- Senior / Principal Machine Learning Engineer, Workers AI- https://job-boards.greenhouse.io/cloudflare/jobs/6297179?gh_...

New comment by kflansburg in "Corrosion"

kflansburg — Mon, 27 Oct 2025 15:05:51 +0000

I see now that this incident happened in September 2024 as well.

New comment by kflansburg in "Corrosion"

kflansburg — Mon, 27 Oct 2025 14:47:21 +0000

Yes, I've already performed the upgrade for my projects, but since they hit this bug, I'm guessing they haven't.

New comment by kflansburg in "Corrosion"

kflansburg — Mon, 27 Oct 2025 14:25:43 +0000

> an if let expression over an RWLock assumed (reasonably, but incorrectly) in its else branch that the lock had been released. Instant and virulently contagious deadlock.

I believe this behavior is changing in the 2024 edition: https://doc.rust-lang.org/edition-guide/rust-2024/temporary-...

New comment by kflansburg in "Finding the Best Sleep Tracker"

kflansburg — Mon, 31 Mar 2025 21:59:36 +0000

I'd love to see this comparison between Garmin and Oura. I ditched Whoop because it was too easy to get 100 sleep scores, but my Garmin watch is much harder to please. I do think it offers better signal, but I've never scored over a 90, so maybe it is too critical?

New comment by kflansburg in "400 reasons to not use Microsoft Azure"

kflansburg — Sat, 01 Mar 2025 03:32:41 +0000

All of the JS features are available in Rust, but some don’t have a first-class SDK API yet and you must use wasm-bindgen.

Python in Cloudflare Workers – Running Pyodide on the Edge [video]

kflansburg — Thu, 18 Jul 2024 22:08:26 +0000

Article URL: https://www.youtube.com/watch?v=ik-B9ojsy1I

Comments URL: https://news.ycombinator.com/item?id=41000210

Points: 2

# Comments: 0

New comment by kflansburg in "Python Cloudflare Workers"

kflansburg — Tue, 02 Apr 2024 17:20:25 +0000

I was responding to your point about isolates and cold starts. Snapshots are unique to Python, but V8 does not seem relevant here, all this is doing is initializing the linear buffer that backs Wasm memory for a particular instance. We have a lot of ideas here, some of which are mentioned in the blog post.

New comment by kflansburg in "Python Cloudflare Workers"

kflansburg — Tue, 02 Apr 2024 16:57:38 +0000

We discussed a separate configuration field for Python version. It’s not technically challenging, this was a design choice we made to simplify configuration for users and encourage more efficiencies in terms of shared dependencies.

Your concerns about V8 would impact JavaScript Workers as well and do not match what we see in production. It is also definitely possible to invoke C++ host functions directly from Wasm with V8.

New comment by kflansburg in "Python Cloudflare Workers"

kflansburg — Tue, 02 Apr 2024 16:05:59 +0000

I believe that your summary misunderstands how we will handle versioning. The pyodide /package versions will be controlled by the compatibility date, and we will be able to support multiple in production at once. For packages like langchain (or numpy as you mentioned) the plan is to update quite frequently.

Could you expand on why you believe V8 will be a limiting factor? It is quite a powerful Wasm runtime, and most of the optimizations we have planned don’t really depend on the underlying engine.

Edit: Also just want to clarify that this is not a POC, it is a Beta that we will continue improving on and eventually GA.

New comment by kflansburg in "Nvidia CEO Jensen Huang announces new AI chips: ‘We need bigger GPUs’"

kflansburg — Mon, 18 Mar 2024 22:43:50 +0000

Run:AI https://news.ycombinator.com/item?id=39738342

New comment by kflansburg in "The Black-Scholes/Merton equation [video]"

kflansburg — Sun, 03 Mar 2024 18:09:07 +0000

You can find an IV that makes sense for a single option with invalid other parameters, but things will break down when you go to price other expirations / strikes.

When trading, you don't want to wait to see an "updated" IV, you would want to respond directly to changes in important and well understood parameters like underlying price.