Ben Vinegar
@benv.ca
Co-founder modem.dev. Before: founding engineer then VPE at
@sentry.io. Organizes Devtools Toronto. 🇨🇦
More: benv.ca
@sentry.io. Organizes Devtools Toronto. 🇨🇦
More: benv.ca
Pinned
Ben Vinegar
@benv.ca
· Sep 30
Modem - Your dev-team's auto-triage Product Manager
Turn support, chat, and analytics into developer-ready context so engineers can decide, fix, and ship faster.
modem.dev
I've come to accept AI will write the majority of code.
So earlier this year I started exploring other ways AI could help developers.
That turned into this company, Modem. We're building an agent that does PM triage work for you and delivers product context to your IDE.
More here: modem.dev 🙏
So earlier this year I started exploring other ways AI could help developers.
That turned into this company, Modem. We're building an agent that does PM triage work for you and delivers product context to your IDE.
More here: modem.dev 🙏
today an engineer found a bug where we over-billed some event types, and made a fix
Modem pinged him - a customer flagged this 2 weeks ago, but it got lost in the noise
he had no idea! so he followed-up & let them know it was addressed
5 mins of setup → never miss a follow-up
Modem pinged him - a customer flagged this 2 weeks ago, but it got lost in the noise
he had no idea! so he followed-up & let them know it was addressed
5 mins of setup → never miss a follow-up
September 16, 2026 at 7:48 PM
today an engineer found a bug where we over-billed some event types, and made a fix
Modem pinged him - a customer flagged this 2 weeks ago, but it got lost in the noise
he had no idea! so he followed-up & let them know it was addressed
5 mins of setup → never miss a follow-up
Modem pinged him - a customer flagged this 2 weeks ago, but it got lost in the noise
he had no idea! so he followed-up & let them know it was addressed
5 mins of setup → never miss a follow-up
🏛️ announcing hunk v0.22.0 - now w/ `hunk log`
- TUI for reviewing git/jj history
- quickly jump from commit → diff
- OR multi-select a commit range
- supports mouse + all colour themes
also in this release: multi-line comments, lower memory usage, more efficient --watch mode, and more! (🔈)
- TUI for reviewing git/jj history
- quickly jump from commit → diff
- OR multi-select a commit range
- supports mouse + all colour themes
also in this release: multi-line comments, lower memory usage, more efficient --watch mode, and more! (🔈)
September 10, 2026 at 12:34 PM
🏛️ announcing hunk v0.22.0 - now w/ `hunk log`
- TUI for reviewing git/jj history
- quickly jump from commit → diff
- OR multi-select a commit range
- supports mouse + all colour themes
also in this release: multi-line comments, lower memory usage, more efficient --watch mode, and more! (🔈)
- TUI for reviewing git/jj history
- quickly jump from commit → diff
- OR multi-select a commit range
- supports mouse + all colour themes
also in this release: multi-line comments, lower memory usage, more efficient --watch mode, and more! (🔈)
the only cli benchmark that matters
September 7, 2026 at 6:23 PM
the only cli benchmark that matters
👀 here's another take on browsing git history inside hunk:
hunk-history (extension)
⬇️ looks pretty nice
hunk-history (extension)
⬇️ looks pretty nice
September 6, 2026 at 1:04 PM
👀 here's another take on browsing git history inside hunk:
hunk-history (extension)
⬇️ looks pretty nice
hunk-history (extension)
⬇️ looks pretty nice
we're now processing a lot of data, which is great
but the days of infrastructure easy mode have come to an end
but the days of infrastructure easy mode have come to an end
September 3, 2026 at 3:05 PM
we're now processing a lot of data, which is great
but the days of infrastructure easy mode have come to an end
but the days of infrastructure easy mode have come to an end
🎙️ State of Agentic Coding w/ @mitsuhiko.at and @benv.ca returns
In this episode (#9):
- how agents are getting more autonomous
- the subsidies will continue until morale improves
- herdr and VC-funded terminal apps
- vibe coding from your car, and more!
Available on YT, Spotify, and via RSS ⬇️
In this episode (#9):
- how agents are getting more autonomous
- the subsidies will continue until morale improves
- herdr and VC-funded terminal apps
- vibe coding from your car, and more!
Available on YT, Spotify, and via RSS ⬇️
August 17, 2026 at 1:59 PM
🎙️ State of Agentic Coding w/ @mitsuhiko.at and @benv.ca returns
In this episode (#9):
- how agents are getting more autonomous
- the subsidies will continue until morale improves
- herdr and VC-funded terminal apps
- vibe coding from your car, and more!
Available on YT, Spotify, and via RSS ⬇️
In this episode (#9):
- how agents are getting more autonomous
- the subsidies will continue until morale improves
- herdr and VC-funded terminal apps
- vibe coding from your car, and more!
Available on YT, Spotify, and via RSS ⬇️
It's becoming normal practice to plug your coding agent into tools like Slack and helpdesk software to find customer insights.
Turns out it's super inefficient, because you're just fetching and smashing raw strings into your context repeatedly.
So we released a new MCP server that solves that.
Turns out it's super inefficient, because you're just fetching and smashing raw strings into your context repeatedly.
So we released a new MCP server that solves that.
July 31, 2026 at 3:35 PM
It's becoming normal practice to plug your coding agent into tools like Slack and helpdesk software to find customer insights.
Turns out it's super inefficient, because you're just fetching and smashing raw strings into your context repeatedly.
So we released a new MCP server that solves that.
Turns out it's super inefficient, because you're just fetching and smashing raw strings into your context repeatedly.
So we released a new MCP server that solves that.
✅ Yes the code matters
In experiments we ran, well-named and organized code can dramatically improve agent outcomes:
- fewer tokens spent/more context window preserved
- fewer confidently wrong answers developed
Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more
In experiments we ran, well-named and organized code can dramatically improve agent outcomes:
- fewer tokens spent/more context window preserved
- fewer confidently wrong answers developed
Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more
👋 New blog post:
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
July 24, 2026 at 2:38 PM
✅ Yes the code matters
In experiments we ran, well-named and organized code can dramatically improve agent outcomes:
- fewer tokens spent/more context window preserved
- fewer confidently wrong answers developed
Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more
In experiments we ran, well-named and organized code can dramatically improve agent outcomes:
- fewer tokens spent/more context window preserved
- fewer confidently wrong answers developed
Verified against 14 model/harness combos incl Sol, Fable, GLM 5.2 and more
👋 New blog post:
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
July 20, 2026 at 2:48 PM
👋 New blog post:
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
"How coding agents read files – and how to write for them"
In it I explain how code optimized for agent-discovery can lead to major token savings on search + retrieval, even with frontier models like GPT-5.6 Sol
Plus other important findings ⬇️
🎙️ State of Agentic Coding #8 with guest Mario Zechner is out. In this episode:
- Vibe-checking Fable & GLM 5.2
- @mitsuhiko.at teaches us RL
- How harnesses smooth out model jank
- Loops, surviving AI fomo, and more
YT: www.youtube.com/watch?v=_lfp...
Spotify: open.spotify.com/episode/6m40...
- Vibe-checking Fable & GLM 5.2
- @mitsuhiko.at teaches us RL
- How harnesses smooth out model jank
- Loops, surviving AI fomo, and more
YT: www.youtube.com/watch?v=_lfp...
Spotify: open.spotify.com/episode/6m40...
July 14, 2026 at 8:17 AM
🎙️ State of Agentic Coding #8 with guest Mario Zechner is out. In this episode:
- Vibe-checking Fable & GLM 5.2
- @mitsuhiko.at teaches us RL
- How harnesses smooth out model jank
- Loops, surviving AI fomo, and more
YT: www.youtube.com/watch?v=_lfp...
Spotify: open.spotify.com/episode/6m40...
- Vibe-checking Fable & GLM 5.2
- @mitsuhiko.at teaches us RL
- How harnesses smooth out model jank
- Loops, surviving AI fomo, and more
YT: www.youtube.com/watch?v=_lfp...
Spotify: open.spotify.com/episode/6m40...
🛠️ hunk 0.17.0 is out
Patches from 10 new contributors, w/ small fixes & quality-of-life improvements like:
- official homebrew install (brew install hunk)
- launch hunk w/o menu bar
- better session reliability
- esc no longer quits, proper transparent bg colours, & more
Patches from 10 new contributors, w/ small fixes & quality-of-life improvements like:
- official homebrew install (brew install hunk)
- launch hunk w/o menu bar
- better session reliability
- esc no longer quits, proper transparent bg colours, & more
July 7, 2026 at 11:56 AM
🛠️ hunk 0.17.0 is out
Patches from 10 new contributors, w/ small fixes & quality-of-life improvements like:
- official homebrew install (brew install hunk)
- launch hunk w/o menu bar
- better session reliability
- esc no longer quits, proper transparent bg colours, & more
Patches from 10 new contributors, w/ small fixes & quality-of-life improvements like:
- official homebrew install (brew install hunk)
- launch hunk w/o menu bar
- better session reliability
- esc no longer quits, proper transparent bg colours, & more
Just noticed a vibe-coded project of mine cost $200/month to serve a few dozen users/day 😭
Turns out it was doing 10s of millions of unnecessary Redis polls/day, even when idle - telemetry alone cost $$
a possible clue for why infra providers are growing so much right now
Turns out it was doing 10s of millions of unnecessary Redis polls/day, even when idle - telemetry alone cost $$
a possible clue for why infra providers are growing so much right now
June 28, 2026 at 1:56 PM
Just noticed a vibe-coded project of mine cost $200/month to serve a few dozen users/day 😭
Turns out it was doing 10s of millions of unnecessary Redis polls/day, even when idle - telemetry alone cost $$
a possible clue for why infra providers are growing so much right now
Turns out it was doing 10s of millions of unnecessary Redis polls/day, even when idle - telemetry alone cost $$
a possible clue for why infra providers are growing so much right now
there's a lot of tech companies in Toronto now
June 13, 2026 at 3:48 PM
there's a lot of tech companies in Toronto now
🎨 hunk v0.15.0 is out:
- supports git --color-moved
- transparent backgrounds
- color token fixes
- more themes
- Sapling support (it's a VCS from Meta)
also now there's a website → hunk.dev
- supports git --color-moved
- transparent backgrounds
- color token fixes
- more themes
- Sapling support (it's a VCS from Meta)
also now there's a website → hunk.dev
June 9, 2026 at 10:00 PM
🎨 hunk v0.15.0 is out:
- supports git --color-moved
- transparent backgrounds
- color token fixes
- more themes
- Sapling support (it's a VCS from Meta)
also now there's a website → hunk.dev
- supports git --color-moved
- transparent backgrounds
- color token fixes
- more themes
- Sapling support (it's a VCS from Meta)
also now there's a website → hunk.dev
A pattern I'm seeing with AI debugging: it's easy to get stuck inside the model's search space.
So you burn tokens & time chasing candidate fixes, while the real answer sits in context only you have ... but never explored, because you quietly surrendered your thinking.
So you burn tokens & time chasing candidate fixes, while the real answer sits in context only you have ... but never explored, because you quietly surrendered your thinking.
June 2, 2026 at 10:09 PM
A pattern I'm seeing with AI debugging: it's easy to get stuck inside the model's search space.
So you burn tokens & time chasing candidate fixes, while the real answer sits in context only you have ... but never explored, because you quietly surrendered your thinking.
So you burn tokens & time chasing candidate fixes, while the real answer sits in context only you have ... but never explored, because you quietly surrendered your thinking.
I would take a bullet for this clanker
May 28, 2026 at 5:18 PM
I would take a bullet for this clanker
hunk 0.14.0 is out w/ lots of user contribs + fixes:
🆕 expand/collapse inline source (vid 👇)
🆕 custom themes
🆕 new theme: catpuccin latte/mocha
🆕 select + copy to clipboard
🆕 renders wide chars like 你好 & emoji properly
🆕 expand/collapse inline source (vid 👇)
🆕 custom themes
🆕 new theme: catpuccin latte/mocha
🆕 select + copy to clipboard
🆕 renders wide chars like 你好 & emoji properly
May 27, 2026 at 1:27 AM
hunk 0.14.0 is out w/ lots of user contribs + fixes:
🆕 expand/collapse inline source (vid 👇)
🆕 custom themes
🆕 new theme: catpuccin latte/mocha
🆕 select + copy to clipboard
🆕 renders wide chars like 你好 & emoji properly
🆕 expand/collapse inline source (vid 👇)
🆕 custom themes
🆕 new theme: catpuccin latte/mocha
🆕 select + copy to clipboard
🆕 renders wide chars like 你好 & emoji properly
Reposted by Ben Vinegar
As expected, another tool by @benv.ca has become part of my workflow - Glance solves the problem of given terminal based agents access to screenshots. It's been super helpful while I'm building by first TUI glance.sh
glance.sh — Share an image with your coding agent
Paste a screenshot, get a temporary URL. Built for terminal environments, coding agents, and CLI workflows where copy/pasting images is hard.
glance.sh
May 7, 2026 at 4:03 PM
In 3 weeks at the next Devtools Toronto:
traces.com - share agent coding sessions
polarity.so - sandboxes for agent testing
superuser.app - agents in your team chat
tidra.ai - AI code maintenance at scale
docsalot.dev - docs agents can read
codepathfinder.dev - trace vulns across your codebase
traces.com - share agent coding sessions
polarity.so - sandboxes for agent testing
superuser.app - agents in your team chat
tidra.ai - AI code maintenance at scale
docsalot.dev - docs agents can read
codepathfinder.dev - trace vulns across your codebase
May 4, 2026 at 2:30 PM
In 3 weeks at the next Devtools Toronto:
traces.com - share agent coding sessions
polarity.so - sandboxes for agent testing
superuser.app - agents in your team chat
tidra.ai - AI code maintenance at scale
docsalot.dev - docs agents can read
codepathfinder.dev - trace vulns across your codebase
traces.com - share agent coding sessions
polarity.so - sandboxes for agent testing
superuser.app - agents in your team chat
tidra.ai - AI code maintenance at scale
docsalot.dev - docs agents can read
codepathfinder.dev - trace vulns across your codebase
State of Agentic Coding #5 with @mitsuhiko.at is live.
In this episode:
- death of the IDE premature?
- what's with all the bugs
- will future models fix yesterday's AI code?
- token abuse, slowing down, and more!
YT: www.youtube.com/watch?v=qCpY...
Spotify: open.spotify.com/episode/7wUV...
In this episode:
- death of the IDE premature?
- what's with all the bugs
- will future models fix yesterday's AI code?
- token abuse, slowing down, and more!
YT: www.youtube.com/watch?v=qCpY...
Spotify: open.spotify.com/episode/7wUV...
April 10, 2026 at 3:01 PM
State of Agentic Coding #5 with @mitsuhiko.at is live.
In this episode:
- death of the IDE premature?
- what's with all the bugs
- will future models fix yesterday's AI code?
- token abuse, slowing down, and more!
YT: www.youtube.com/watch?v=qCpY...
Spotify: open.spotify.com/episode/7wUV...
In this episode:
- death of the IDE premature?
- what's with all the bugs
- will future models fix yesterday's AI code?
- token abuse, slowing down, and more!
YT: www.youtube.com/watch?v=qCpY...
Spotify: open.spotify.com/episode/7wUV...
My terminal diff tool, hunk, has added a lot of good stuff:
- horizontal scrolling w/ mouse support
- pinned file headers
- way better file browser UI
- draggable scrollbar
- perf & bug fixes
⬇️ Here's what it looks like today
- horizontal scrolling w/ mouse support
- pinned file headers
- way better file browser UI
- draggable scrollbar
- perf & bug fixes
⬇️ Here's what it looks like today
April 9, 2026 at 5:15 PM
My terminal diff tool, hunk, has added a lot of good stuff:
- horizontal scrolling w/ mouse support
- pinned file headers
- way better file browser UI
- draggable scrollbar
- perf & bug fixes
⬇️ Here's what it looks like today
- horizontal scrolling w/ mouse support
- pinned file headers
- way better file browser UI
- draggable scrollbar
- perf & bug fixes
⬇️ Here's what it looks like today
Montreal's Metro is the 4th-busiest rapid transit system in North America
But for brutalist vibes, it's unmatched
But for brutalist vibes, it's unmatched
April 4, 2026 at 6:07 PM
Montreal's Metro is the 4th-busiest rapid transit system in North America
But for brutalist vibes, it's unmatched
But for brutalist vibes, it's unmatched
I've been building a terminal diff tool for agentic code review:
- agent comments + agent remote control
- syntax highlighting
- auto-responsive layouts (stacked & split)
- file browser
- mouse support
- uses OpenTUI + Diffs from Pierre Computer Co
- agent comments + agent remote control
- syntax highlighting
- auto-responsive layouts (stacked & split)
- file browser
- mouse support
- uses OpenTUI + Diffs from Pierre Computer Co
March 23, 2026 at 3:11 PM
I've been building a terminal diff tool for agentic code review:
- agent comments + agent remote control
- syntax highlighting
- auto-responsive layouts (stacked & split)
- file browser
- mouse support
- uses OpenTUI + Diffs from Pierre Computer Co
- agent comments + agent remote control
- syntax highlighting
- auto-responsive layouts (stacked & split)
- file browser
- mouse support
- uses OpenTUI + Diffs from Pierre Computer Co
Coding was never the slow part.
That's why we built Modem, your dev team's auto-triage PM.
It listens to user signals 24/7, finds problems before you do & does the in-between work – filing tickets, pinging teammates, closing the loop.
And it's not vaporware! You can try it out today at modem.dev
That's why we built Modem, your dev team's auto-triage PM.
It listens to user signals 24/7, finds problems before you do & does the in-between work – filing tickets, pinging teammates, closing the loop.
And it's not vaporware! You can try it out today at modem.dev
March 3, 2026 at 7:09 PM
Coding was never the slow part.
That's why we built Modem, your dev team's auto-triage PM.
It listens to user signals 24/7, finds problems before you do & does the in-between work – filing tickets, pinging teammates, closing the loop.
And it's not vaporware! You can try it out today at modem.dev
That's why we built Modem, your dev team's auto-triage PM.
It listens to user signals 24/7, finds problems before you do & does the in-between work – filing tickets, pinging teammates, closing the loop.
And it's not vaporware! You can try it out today at modem.dev