This is what I wanted agent observability to feel like. Traces that end in a code change.

It was great working with @oliveholistic to improve their product experience! If you want faster and cheaper inference at frontier model quality, shoot me a DM.

Shout out to @samhogan @AmarSVS @francescodvirga @atbeme @mikepollard_dev and the rest of the Inference dot net team

Install our SDK, collect traces, improve your agents.

We're releasing Schematron V2, a family of Specialized Language Models for converting messy HTML to structured JSON frontier performance at 1/10th the cost Schematron V2 was designed in partnership with some of the largest web-scraping companies in the world to meet the demands of their heaviest workloads Schematron-V2-Turbo and Schematron-V2-Small are available today on @inference_net Get started: docs.inference.net/workhorse…

Come train a custom model

More Inference events coming soon so stay tuned!

PodSnacks is probably my favorite daily email. News from everything I’m interested in all in one place.

Come hang out with @samhogan and I. These dinners are always a great time.

Day Zero fine-tuning & hosting support for Nemotron 3 Super by @nvidia is now live Fine-tune on real production traces & deploy on high-performance infrastructure optimized for Nemotron 3 Super Your data, your weights, your performance edge Learn more: inference.net/blog/nemotron-…

Going to open source our own internal version of this soon. It’s called Gator and it rocks

What if a codebase was actually stored in Postgres and agents directly modified files by reading/writing to the DB? Code velocity has increased 3-5x. This will undoubtedly continue. PR review has already become a bottleneck for high output teams. Codebase checked-out on filesystem seems like a terrible primitive when you have 10-100-1000 agents writing code. Code is now high velocity data and should be modeled at such. Bare minimum, we need write-level atomicity and better coordination across agents, better synchronization primitives for subscribing to codebase state changes and real-time time file-level code lint/fmt/review. The current ~20 year old paradigm of git checkout/branch/push/pr/review/rebase ended Jan 2026. We need an entirely new foundational system for writing code if we’re really going to keep pace with scale laws.

Introducing our new Schematron benchmark. We took some time to compare all of the latest open source models to see which one takes the crown. The benchmark essentially measures the ability of LLMs to take raw HTML along with a JSON schema, and then fill out that schema. We measure things like recall/precision, hallucinations, and ability to handle ambiguity. The benchmarks are graded with an ensemble of frontier models on a 5 point rubric. We can see that GLM 5 is the best open source model currently for schema extraction. Surprisingly, GPT-OSS 120B does very well at these type of extraction tasks as well. Another interesting result is we noticed degradation of quality using Qwen3.5 Plus on this task versus the original Qwen3.5 397B MOE. The inputs can be up to 120K tokens, so this is akin to a long context benchmark, with an additional reasoning layer. We will be open sourcing this benchmark if it gains sufficient traction. Also, more benchmarks coming from our side!

Vibe coding is the new product management. Training and tuning models is the new coding.

We're welcoming @mikepollard_dev to @inference_net as our Founding DevRel Engineer! Mike and I won a pitch competition for my first company nearly 7 years ago Life is long. When you find someone you love to work with, keep them close. You never know when your paths may cross

Bought my gf an espresso machine and now I'm forced to drink 6 cups a day while she fine tunes the grind size and tamping methods

Algorithmic short form videos aren't enough anymore. When can we get 0.5s AI-generated bursts that just cook the receptors directly?

I am a machine that turns zyns and caffeine into half-finished b2b saas

Dinner Number 1 was a resounding success! Dinner Number 2 is Sept 5. 10 seats. Private dining room at a classic spot in the heart of SF. DM me to come :) Going to do 5 more of these and then throw a bangin’ party with everyone

I like to refer to the ^ character in my package.json as the break your app randomly character.