Ben Bleikamp

377 posts

Ben Bleikamp banner
Ben Bleikamp

Ben Bleikamp

@bleikamp

software designer, co-founder at https://t.co/BXD0uWLe3L, prev. head of design @github, built design tools @meta, long time surfer of the information superhighway

Mill Valley Katılım Mart 2008
714 Takip Edilen4.2K Takipçiler
Ben Bleikamp
Ben Bleikamp@bleikamp·
Building tiny tools is so fun+fast now catmd is a Markdown viewer that lets me read and see realtime updates as I work with agents writing Markdown for specs, plans, etc.
Ben Bleikamp tweet media
English
0
0
5
650
Ben Bleikamp
Ben Bleikamp@bleikamp·
OpenClaw has 3,500 open PRs, many with hundreds of comments from AI code reviewers. Implementing an idea used to be kind of a pain and came with a bit of friction. You had to actually think about whether the idea was good enough and worth trying to convince maintainers to merge. The friction was good, it was a bit of a filter. Feels like the end of open source—the slop seems completely unmanageable for popular projects
English
1
0
2
310
Ben Bleikamp
Ben Bleikamp@bleikamp·
Do you guys do an evals or anything on the difference? In practice we've found a basic Sentry CLI we built + Claude Code got us either identical or slightly better results; in rare cases Seer might do something marginally more correct, but not $40/mo/user more correct. To be fair our issues aren't very complex, just curious how you're thinking about it
English
1
0
0
107
David Cramer
David Cramer@zeeg·
@bleikamp Seer does a ton of analysis that claude code cant but the CLI (issue explain) I think pulls the seer data, similar to how we do it in the MCP as well
English
1
0
2
320
Ben Bleikamp retweetledi
Benji Taylor
Benji Taylor@benjitaylor·
Introducing Agentation: a visual feedback tool for agents. Available now: ~npm i agentation Click elements, add notes, copy markdown. Your agent gets element paths, selectors, positions, and everything else it needs to find and fix things. Link to full docs below ↓
English
241
376
4.5K
696.5K
Ben Bleikamp
Ben Bleikamp@bleikamp·
@jacobgold how do you win SDLC without the best coding model? most of these companies aren't even in the running, imo
English
1
0
1
42
Jacob Gold
Jacob Gold@jacobgold·
@bleikamp its not about winning the subsector anymore, i think. its about winning end to end
English
1
0
2
71
Ben Bleikamp
Ben Bleikamp@bleikamp·
Cognition, Linear, Sentry, Anthropic, OpenAI, Greptile, Cursor, Graphite, and probably a dozen more start ups Seems impossible that there is any durable ARR in this space? Are all of the incumbents just out of ideas?
Cognition@cognition

Meet Devin Review: a reimagined interface for understanding complex PRs. Code review tools today don’t actually make it easier to read code. Devin Review builds your comprehension and helps you stop slop. Try without an account: devinreview.com More below 👇

English
1
0
3
563
Ben Bleikamp retweetledi
Ramit Sethi
Ramit Sethi@ramit·
Do not look away. You are living through history Conservatives have unleashed thousands of masked militiamen across America, arresting, assaulting, even killing innocent people This is one of our country's most shameful chapters
David J. Bier@David_J_Bier

Photographer @mostafabassim1 photographed this boy walking home alone with a snack being "randomly" approached by DHS. "After he was unable to produce documentation proving his citizenship, agents informed him that he was under arrest." He said, "Can I just go home?" Answer: No.

English
346
2.4K
8K
279.2K
Ben Bleikamp
Ben Bleikamp@bleikamp·
@jeffzwang I ended up just building a thing as an internal tool, one click to turn anything in the inbox into a Claude Code task. x.com/bleikamp/statu…
Ben Bleikamp@bleikamp

Spent the weekend with Claude Code and Codex (5.2 xhigh, ofc) replacing Notion and Linear for our (tiny) 4-person team We were hacking together something simple with a few complex tools. So I just built the simple thing we wanted. - Markdown files are the datastore, all on a Fly.io volume, YAML frontmatter for structured data - SOTA model agent loop - Manage everything via Slack commands - Notion-style web UI for writing - Auth via GitHub

English
0
0
1
268
Jeffrey Wang
Jeffrey Wang@jeffzwang·
I need Linear but where every task is automatically an AI agent session that at least takes a first stab at the task. Basically a todo list that tries to do itself
English
127
9
713
142.2K
Ben Bleikamp
Ben Bleikamp@bleikamp·
Spent the weekend with Claude Code and Codex (5.2 xhigh, ofc) replacing Notion and Linear for our (tiny) 4-person team We were hacking together something simple with a few complex tools. So I just built the simple thing we wanted. - Markdown files are the datastore, all on a Fly.io volume, YAML frontmatter for structured data - SOTA model agent loop - Manage everything via Slack commands - Notion-style web UI for writing - Auth via GitHub
Ben Bleikamp tweet mediaBen Bleikamp tweet media
English
7
1
15
2.4K
Ben Bleikamp
Ben Bleikamp@bleikamp·
Agents are *so* good at reading `--help` from a CLI and figuring out what to do. I always wondered why people use `gh` for GitHub, now it's become my main interface to the product. I barely look at the app.
English
0
0
1
89
Ben Bleikamp
Ben Bleikamp@bleikamp·
For any very frequent task I have just started writing CLIs and creating a Skill the agent can use. - Explain the to agent what you want to do - Ask it to create a README for the CLI - Iterate on the README to ensure it will solve your use case - Tell the agent to build the CLI I have a Google Calendar CLI that powers my daily note in Obsidian; it took 15 minutes to build.
DHH@dhh

We've been exploring the value of letting agents use CLIs vs just navigating a REST API directly. The smartest models can do without a CLI, but take longer and cost more. Even small models can succeed when given CLIs. But the puck keeps moving!

English
1
0
1
204
Max Schoening
Max Schoening@mschoening·
In the last 5 years, I was wrong about LLMs: - 2020: I got a demo of GitHub Copilot – at the time it was an issue-to-pr bot. It sucked. Then, @alexgraveley showed me ghost text completion and disabused me of that belief. - February 2024: I was building an agent UI (think @conductor_build) at my previous gig and thought: "The models aren't good enough for this to be a good experience." In June, Claude 3.5 Sonnet disabused me of that belief. - May 2025: We were exploring agentic coding at Notion: "The models aren't good enough if you don't already know how to code." In December, Opus 4.5 and GPT-5.2 disabused me of that belief. In 2026, I hope I will be wrong again, but I also believe what we have now is ~AGI for everything that can be represented as code (aka a lot).
Simon Willison@simonw

It genuinely feels to me like GPT-5.2 and Opus 4.5 in November represent an inflection point - one of those moments where the models get incrementally better in a way that tips across an invisible capability line where suddenly a whole bunch of much harder coding problems open up

English
20
12
277
56.8K