Top all-time · #5000
Tessl
Company blog · tessl.io/blogaiprogramming
Tessl is the company blog at tessl.io, writing about ai and programming. Since 2024, 16 different Hacker News readers have linked it 32 times, most often “Jev is 13.6x faster, 2.7x cheaper than GPT Luna 6”. It is still writing: the last post was on 2026-10-28, and you can follow it by feed.
Too few sampled comments (7) to say how often HN recommends it.?
Why HN links it
HN readers link Tessl's blog for posts on AI coding agents, including evals of agent skills, a benchmark of the Jev classifier against other approaches, and literate programming in the agent era.
Summarised by Claude from a sample of 7 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Tessl helps teams build AI-native software by giving coding agents structured, versioned context. Ship AI-powered systems that hold up in real codebases.
Most-linked posts?
- Jev is 13.6x faster, 2.7x cheaper than GPT Luna 62 people · 2 mentions · first linked 2026-09-23
What Hacker News says?
It may interest you that Guy Podjarny, one of the Snyk founders, now has an AI coding company ( https://www.tessl.io/about ) that looks like a competitor of yours
Comment linking /about
on “Snyk security researcher deploys malicious NPM packages targeting cursor.com”Submitted Tessl raises $125M for a zero maintenance, spec-centric AI software dev platform as a story · 24 points
HN discussionAlso interestingly the Snyk cofounder has started a competitor to cursor https://www.tessl.io/ https://techcrunch.com/2024/11/14/tessl-raises-125m-at-at-50... I hope there is no foul play.
Comment linking /
on “Snyk security researcher deploys malicious NPM packages targeting cursor.com”Submitted Haiku 4.5 + skills outperforms Opus 4.7. 9 models tested with and without skills as a story · 4 points
HN discussionYes. Not as fast/cheap as Typesafe claims, but lots of benchmarks suggest around 3-4 times cheaper, and 7-14 times faster. - https://www.ml6.eu/en/blog/jev-vs-gpt-6-luna-vs-bert-text-cl... - https://tessl.io/blog/jev-is-136x-faster-and-27x-cheaper-tha... - https://x.com/fazxes/status/2100300097695232164 (this last one is Luna 5.6 but that isn't too different from 6 besides accuracy and cost)
Comment linking /blog/jev-is-136x-faster-and-27x-cheaper-than-gpt-luna-6-for-tessl-verifiers-try-it-yourself
on “Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers”Submitted Agents.md file isn't the problem. Your lack of Evals is as a story · 4 points
HN discussionThe agents are smart enough to write the evals too. It's agents all the way down! Submit a GitHub repo containing skills to Tessl, and it will generate the evals, run them, and present the results. https://tessl.io/registry/skills/submit The evals and results are all shown, no login necessary, so you can assess them yourself. e.g. https://tessl.io/registry/skills/github/coreyhaines31/market... (click details to see…
Comment linking /registry/skills/github/coreyhaines31/marketingskills/content-strategy/evals
on “Agents.md file isn't the problem. Your lack of Evals is”Submitted Experimenting with Claude 3.5's New Artifacts Feature: A Designer's Journey as a story · 4 points
HN discussionI agree it's worth revisiting. Actually I wrote about this recently, I didn't realise there was a precedent here. https://tessl.io/blog/how-to-capture-intent-with-coding-agen... > As a benefit, the code base can now be exported into many formats for comfortable reading. This is especially important if the primary role of engineers is shifting from writing to reading. Underrated point. Also, whether we like it or not…
Comment linking /blog/how-to-capture-intent-with-coding-agents/
on “We should revisit literate programming in the agent era”Submitted What 1,281 agent runs reveal about coding agent failure in large codebases as a story · 3 points
HN discussionLink to all the review scans is here - mostly in the 50-70% range https://tessl.io/registry/skills/github/googleworkspace/cli
Comment linking /registry/skills/github/googleworkspace/cli
on “Googleworkspace/CLI isn't optimized – Test your skills”Submitted Jev is 13.6x faster, 2.7x cheaper than GPT Luna 6 as a story · 2 points
HN discussionThere's so much more we can do around activation and skills creation. Looking at the eval results, there are even cases where the context makes the agent worse. Scenario 5, test 1 72% -> 22% https://tessl.io/eval-runs/019cc02f-bb26-76e0-a7c9-598a7337e...
Comment linking /eval-runs/019cc02f-bb26-76e0-a7c9-598a7337edb7
on “Googleworkspace/CLI isn't optimized – Test your skills”Submitted A Proposed Framework for Evaluating AI Agent Skills as a story · 2 points
HN discussionSubmitted Show HN: A package manager for agent skills with built-in evals as a story · 2 points
HN discussionSubmitted If agents use your tool, you need evals as a story · 2 points
HN discussionSubmitted AI with IaC – "80% of the value is in codifying 20% of the assumptions" as a story · 2 points
HN discussionSubmitted Snyk founder, Guy Podjarny, creates new AI Native startup, Tessl as a story · 2 points
HN discussionSubmitted Will AI Native Dev Follow Cloud Native's Path? as a story · 2 points
HN discussionSubmitted Best thing I read today, "how open is your software factory" as a story · 1 points
HN discussionSubmitted Why multi-agent AI breaks in prod and how Yugabyte's Meko is trying to fix it as a story · 1 points
HN discussionSubmitted I Built an AI PR Reviewer That Catches Bugs by Not Looking for Bugs as a story · 1 points
HN discussionSubmitted OpenClaw for Dummies (getting to a minimum viable OpenClaw agent) as a story · 1 points
HN discussionSubmitted A 'high blast radius': Amazon probes surge in outages linked to AI coding tools as a story · 1 points
HN discussionSubmitted Claude Code model comparison: Skill usage as a story · 1 points
HN discussionSubmitted Googleworkspace/CLI isn't optimized – Test your skills as a story · 1 points
HN discussionSubmitted The Context Development Lifecycle: Optimizing Context for AI Coding Agents as a story · 1 points
HN discussionSubmitted Skills on Tessl: the package manager for agent skills as a story · 1 points
HN discussionSubmitted Kilo bets on context as the bridge between AI coding agents and chat apps as a story · 1 points
HN discussionSubmitted Chris Messina: Code as Commodity as a story · 1 points
HN discussion
