Mike Pollard

building in SF @inference_net

[Mike Pollard @mikepollard_dev]

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

[Mike Pollard @mikepollard_dev]

@andrewmccalip How do you prevent developers from just click farming?

If they get 50% of the click revenue every click is financially incentivized and a low-quality lead by default without benefit to the advertiser.

[Mike Pollard @mikepollard_dev]

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.

[Inference @inference_net]

Specialized models are becoming a practical path to better AI UX.

Olive moved from a frontier model to a custom model trained with Inference Catalyst for their food verdict workflow.

After a user scans a product, the model now delivers near-instant verdicts on what to watch out for, making the in-store experience faster and more seamless while cutting inference cost significantly.

Results:
- p50 latency: 2,721ms → 591ms
- p99 latency: 6,414ms → 998ms
- time to first word: ~0.25s
- inference cost: ~70% lower

Great working with @oliveholistic on this!

Full case study here: https://t.co/4j3rXJcrHU

[Zach Oldham @zachtheoldham]

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

[Mike Pollard @mikepollard_dev]

@benhylak @hnshah Check out @inference_net We track every request across every provider and you get insight into the aggregated result and the cost of each individual inference.

[Mike Pollard @mikepollard_dev]

Install our SDK, collect traces, improve your agents.

[Sam Hogan 🇺🇸 @samhogan]

3 weeks ago we open-sourced HALO

this led to talking with dozens of teams running agents at scale

we realized the current agent monitoring tools aren't built for the future that we so clearly see ahead of us

today we’re releasing native OpenTelemetry-compatible agent tracing on @inference_net, powered by the same open-source core behind HALO

[Sam Hogan 🇺🇸 @samhogan]

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: https://t.co/8ojqgqnDqx

[Mike Pollard @mikepollard_dev]

Come train a custom model

[Sam Hogan 🇺🇸 @samhogan]

Introducing Catalyst: a developer platform to monitor, train & deploy self-improving AI models

built for teams operating AI products at scale

Catalyst can automatically:
- collect traces from your agents
- curate training data & evals
- train & deploy models on par w/ Opus 4.6

[Mike Pollard @mikepollard_dev]

More Inference events coming soon so stay tuned!

[Josh @0ximjosh]

Absolute blast with @inference_net @sentry and @PlanetScale in SF. I need to work on recreating this in Austin 👀

[Mike Pollard @mikepollard_dev]

@abhijitwt Because Typescript is great

[Mike Pollard @mikepollard_dev]

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

[Shimon @sir]

I'm biased but the Headlines email from @PodSnacks is my favorite source of news rn

[Mike Pollard @mikepollard_dev]

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

[Sam Hogan 🇺🇸 @samhogan]

I’m hosting dinner parties again.

8-10 people, twice per month in San Francisco.

If you are a founder, and especially if you are NOT a founder, and you would like to come for an evening of good food and conversation, send me a DM

First dinner is March 27

[Mike Pollard @mikepollard_dev]

@NicoCosmic @Anubhavhing Exactly, there are much better alternatives where you have more control

[Mike Pollard @mikepollard_dev]

@Anubhavhing Well this was already a thing with firecrawl and nothing huge happened so I don’t imagine this would be much different. Cloudflares also self identifies as a bot so can get blocked more easily. Schematron-3b is the best model for extracting good page data for the cost.

[Inference @inference_net]

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: https://t.co/VoLBVnq49z

[Sam Hogan 🇺🇸 @samhogan]

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

[Sam Hogan 🇺🇸 @samhogan]

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.

[Mike Pollard @mikepollard_dev]

@solofounders It’s literally in the name, solo founder. Most decided to do this solo without the headache of hiring and partners.

[Amar Singh @AmarSVS]

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!

[Mike Pollard @mikepollard_dev]

@milesdeutscher if your'e doing this instead of renting VPS's you're cooked