FastRender
Shares rank 45 of 53 web browsers by recommenders
Recommended as a proof of concept for what coding agents can build, though critics say it barely renders and ignores web standards.
Recommended as a proof of concept for what coding agents can build, though critics say it barely renders and ignores web standards.
25 people gave an opinion
- recommend it
- 6
- criticize it
- 19
- approval share
- 24%
Recommended in 2 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 0.3 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Proof of concept for coding agents
“I don't think it detracts much if at all from FastRender as an example of what an army of coding agents can help a single engineer achieve”
Comment from 20 Jan 2026 in “Scaling long-running autonomous coding” “a pretty great proof of concept that illustrates a path forward to doing better”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” Documents what agents can and cannot do
“one of the first that describes a large scale experiment of agents, what works, what doesn't”
Comment from 27 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” “The blog post itself is one of the first that describes a large scale experiment of agents”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” Renders pages surprisingly well
“I've tried it and it works surprisingly well”
Comment from 18 Jan 2026 in “Cursor's latest "browser experiment" implied success without evidence” “"It kind of works" is a fair assessment IMO!”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” “It's functional enough to render web pages”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents”
What people warn about
Each mark is one comment
Poor architecture, ignores web standards
“This rendering loop architecture makes zero sense, and it does not implement web standards.”
Comment from 21 Jan 2026 in “Scaling long-running autonomous coding” “a uniquely bad design that could never support anything resembling a real-world web engine”
Comment from 21 Jan 2026 in “Scaling long-running autonomous coding” “the code is quite frankly a bunch of spaghetti that does not follow Web standards at all”
Comment from 21 Jan 2026 in “Scaling long-running autonomous coding” - Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents”
Barely works, little practical use
“The one that people couldn't compile, and was largely a failed attempt to stitch together existing libraries?”
Comment from 28 Jan 2026 in “Show HN: One Human + One Agent = One Browser From Scratch in 20K LOC” “I am frustrated at people loudly and proudly "releasing" a system they claim works when it does not.”
Comment from 26 Jan 2026 in “When AI 'builds a browser,' check the repo before believing the hype” “some premade libraries duct taped together into a crappy browser that barely works”
Comment from 25 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” - Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents”
Hype over real engineering
“autonomous slop" seen in projects like fastrender that claim to build complex software with AI but produce what I call "fine-looking nonsense"”
Comment from 25 Feb 2026 in “Implementing WebNN with the Help of AI” “Writing (or generating) a million lines of code in Rust should not count as an achievement in and of itself.”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” “this wasn't a browser project - he outsourced almost all of the browser design thinking to the agents”
Comment from 24 Jan 2026 in “Wilson Lin on FastRender: a browser built by parallel agents” - Comment from 1 Aug 2026 in “Google fixed more Chrome bugs in June than over the past two years, thanks to AI”
Other web browsers people recommend
The four most recommended other web browsers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Firefox | 1,572 | 1,371 | 53% | 12 | 16 yrs125 owners | — |
| Google Chrome | 503 | 1,086 | 32% | 12 | 10 yrs11 owners | — |
| Brave | 397 | 248 | 62% | 12 | 4.9 yrs16 owners | — |
| Safari | 307 | 577 | 35% | 12 | 13 yrs27 owners | — |
| FastRenderThis page | 6 | 19 | 24% | 2 | — | — |
What people said
40 of the 46 comments that mention it, newest first. Each links to the original comment.
“The goal of that project wasn't to produce a web browser, it was to market Cursor”
“no one's taken Cursor's fastrender to production”
“it was neither without dependencies nor actually worked”
“Don't know why no one's picked that up and run with it yet.”
“much cleaner and seems much more complete at first glance”
“embedding-shapes went and undermined it with 20,000 lines of single-agent Rust”
“autonomous slop" seen in projects like fastrender that claim to build complex software with AI but produce what I call "fine-looking nonsense"”
“Far superior, and more cost effective, than the attempt at scaling autonomous agent coding pursued by Fastrender.”
“The one that people couldn't compile, and was largely a failed attempt to stitch together existing libraries?”
“much more superior than Cursor's "browser" from an engineering perspective”
“one of the first that describes a large scale experiment of agents, what works, what doesn't”
“it's a fraction of the size (20,000 lines of Rust compared to ~1.6m)”
“I am frustrated at people loudly and proudly "releasing" a system they claim works when it does not.”
“the rendered pages are slow and have visual glitches”
“some premade libraries duct taped together into a crappy browser that barely works”
“FastRender on the other hand is just this humongous pile of spaghetti”
“The blog post itself is one of the first that describes a large scale experiment of agents”
“Current coding agents are not up to the task of producing a production-quality web browser.”
“a pretty great proof of concept that illustrates a path forward to doing better”
“useless even as a proof of concept”
“this wasn't a browser project - he outsourced almost all of the browser design thinking to the agents”
“not total spaghetti that even gets the spec wrong”
“the output is useless even as a proof of concept web engine”
“spaghetti code that does not implement the spec”
“They achieved that. Looks like a success to me.”
“I'm calling Fastrender not a research project but propaganda.”
“"It kind of works" is a fair assessment IMO!”
“Writing (or generating) a million lines of code in Rust should not count as an achievement in and of itself.”
“It's functional enough to render web pages”
“my impression is that HN exaggerated many of the issues with it”
“I can't imagine this browser being used outside of tinkering or curiosity toy”
“a uniquely bad design that could never support anything resembling a real-world web engine”
“the code is quite frankly a bunch of spaghetti that does not follow Web standards at all”
“This rendering loop architecture makes zero sense, and it does not implement web standards.”
“the code is extremely bad from a conceptual perspective”
“I don't think it detracts much if at all from FastRender as an example of what an army of coding agents can help a single engineer achieve”
“I've tried it and it works surprisingly well”
“Looks like it doesn't compile for at least one other guy”
“I guess they should've left it in a better state before doing that blog post.”
“This looks like extremely brittle code to my eyes.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.