Connect with the Product Hunt community

Now that we have some distance from the initial AI boom, can you say whether AI took your job or improved it?

I definitely felt the impact in the first half of 2024.

Hey everyone! We just shipped v1.11.0 for macOS.

No more password prompt every session

This is the big quality-of-life fix. Approve SideDisplay once under System Settings > General > Login Items & Extensions (under Background App Activity), and starting and stopping just works from then on. No more entering your password every time you connect. (If you'd rather not approve it, nothing changes and you'll be asked for the password as before.)

Building AiSDR has made me rethink how much of sales can be solved by automating the tasks.

We started with prospect research, writing outreach, and handling replies. But I kept joining customer calls to help answer more basic questions: Who should we target? What should we offer? Why would someone care right now? What should we change when nobody responds?

I really like seeing how many enthusiastic male founders are here, but sometimes I find myself looking for more female founders and their stories.

I ve personally faced some of the stereotypes around this that women are usually more cautious, don t take as many risks (including business risks), and that the ideal path is to have a stable job and follow a more traditional way.

I realized recently my bookmark bar is basically a graveyard of articles and tools I thought I d read later. It s reached the point where searching through them takes longer than just Googling the page again.

Really want to avoid adding another subscription service just to organize web links.

What simple habits or native browser tricks are you using to clear out links you don't need anymore?

Many makers have shared the same experience: posts about what broke are 1000x more interesting than posts about polished things that are working perfectly =D

And sometimes, nothing is actually broken.
You just discover something that makes you change direction.

For us, we built a CMS where users could create their own pages:

userpage/ourdomain.com

Hey everyone

Small release, but it's the kind I find interesting: nobody broke this one. It broke by itself, the day macOS 27 shipped.

Termexo v0.10.4 is live. Grok Build joins Claude Code, Codex, OpenCode, and Antigravity in our Windows terminal workbench.

With Grok Build CLI installed and signed in, you can launch it in a workspace, list and resume sessions, and use it on the task board. The usage panel now recognizes an exhausted free allowance, while an unknown percentage stays unavailable instead of appearing as 0%.

This release also fixes a frustrating long-session issue: the session change count could fall to zero and the Git panel go blank after the app had been open for a while. Changed files and diffs now keep refreshing.

Terminals now show a startup animation instead of the launch command. Claude Code accepts Ctrl+V, workspaces can be reordered by dragging, and the duplicate task-board Settings button is removed.

Thank you all for being part of the launch yesterday, all the people I got to meet, all the experiences throughout the day, the pitches, the competition... that's all part of it, and I couldn't be happier

I also got some really nice insights about Toone from the community. A lot of people showing genuine interest in the tool and in what comes next.

I don't want to spoil too much, but we have a mobile application coming for iOS that will allow you to control Toone, dispatch and watch routines, and talk to an agent as if it were running on your machine. Apple just gotta approve.

We've also already implemented a sharing functionality for routines, allowing people to make their expertise and workflows available to the public.

Does every SaaS product need a mobile version?

For some products, mobile feels essential.
For others, it feels like forcing a desktop workflow onto a smaller screen.

We re building a mobile version for RunEvr - mainly to stay up to date, chat with the team, check project progress, and quickly respond when you re away from your desk.

A few things I m curious about:

Watch on YouTube:

Guys! We re fighting for number 1 in the GPT-6 astra challenge today!
Thank you so much for all your support! We re currently at number 2, and we are going up fast!
Every support will help us hit the top spot and hang in until the end. Thank you so much for your upvotes, comments, and everything! Try MosMos!
https://www.producthunt.com/prod...

A new NBER paper tracks 500,000+ GitHub developers against their actual AI telemetry. The task-level gains are enormous and they mostly don't survive the trip to a shipped release. Across four app marketplaces: a sharp rise in new apps, no rise in total usage.

Most of the AI-productivity argument you've read this year is two camps shouting single numbers at each other. There's a paper out that makes both camps right and is more useful than either, and the revised version went up this month, so it's worth twenty minutes before you write your Q4 plan.

I d love to share a few things I figured out while preparing our Product Hunt launch - and I'd love for experienced makers and hunters to add their own advice.

Here s what I learned:

Cover video

If possible, include real people even briefly. Seeing the makers behind a product can create more trust and connection.

In August one coding-agent CLI's release note took its task-tracking tools away from its newest models and kept them for the older ones, with an environment variable to reverse it. The note gives no reason. A component study posted in mid-September is the nearest thing to the arithmetic behind a call like that: a harness part is built to cover for something the model does badly, and the same part does a different job once the model stops doing that thing badly.

The study held an agent loop fixed and swapped parts across four models of different size. Its planning scaffold, a plan re-injected every turn, added 11.6 points on the repository benchmark for the smallest model, whose median run otherwise ended after five turns, two runs in three without an edit. For the largest it trimmed cost by about 30% with a two-point drop in success, because what it cut was verification the model would otherwise keep doing. A predefined tool set showed the same crossover: worth 15 points to the small model on the repository benchmark, while the large one did better there and 53% cheaper with bash alone, bundling several edits into one script.

Our reading: whether a part helps is a question about the model, the task and the budget; what the part costs, in tokens on every turn, is charged whatever the answer. A part that was right when it shipped can be wrong a model generation later without anyone touching it.

We tried the smallest version on our own setup: one small task, one model, fifteen runs, five under each of three tool lists. Every run passed the same four checks. With the task-tracking tools switched back on, the model was offered them in every run and called them zero. With bash alone it finished in a median of 10 turns instead of 17, and the first request carried a quarter of the context. We kept the typed file tools on anyway, because path permission rules attach to them and cannot see inside a shell script.

The large AI labs (Anthropic, OpenAI, Grok, Gemini, etc) are constantly releasing new versions and improvements.

People on social media often advocate for one specific model claiming that it performs tasks better than others.

Hi everyone maker here. Thanks for taking a look at Holon during our Product Hunt launch.

Holon is a local-first workbench for agents that keep following a task beyond a single conversation. They work in your repositories, track progress in durable WorkItems, and wait for events such as CI results or incoming messages before continuing.

Since launch, we've shipped v0.43.0, v0.44.0, and v0.44.1. The v0.44.1 update includes improvements to memory indexing, idle scheduling, and file links across workspaces.

If you're wondering what that looks like in practice, we've also shared three longer reads on X:

I'm signed into 19 Google accounts on this Mac. Most are for different projects, a few are family. Chrome profiles handle it, but every profile is its own window, and at 19 that gets messy fast.

For a while I used Sidekick, which kept each app in its own container, so two accounts of the same service could sit open side by side. Then it shut down.

What are you using for this now? Chrome profiles, a separate browser per account, containers, something else?

I keep going back and forth on this. Write out a tight spec first (user story, edge cases, acceptance criteria) and the AI output gets a lot more predictable, but it also kills a chunk of the speed that made vibe coding appealing in the first place. Skip the spec and just describe the vibe, and I end up rewriting prompts three or four times to fix things a spec would've caught upfront. Where do people here actually land? Full spec, loose bullet points, or just winging it and iterating in the chat?

Curious if this is just me or other devs face it too. I use Jira and GitHub MCPs inside claude code to fetch my tickets and complete them as autonomously as possible.

But it always keeps messing up finding the correct repos, branching properly or delivering a PR without CI failing. And I end up repeating instructions and copy-pasting CI errors and asking to fix it. I tracked this and I spent on avg 75mins a day repeating context and instructions.

Anyone also facing this or found a way around it?

It doesn't even have to be a big dramatic failures, more the small moments where something clicked and you went from trusting the output by default to double checking everything. For me it was watching an agent confidently rename a function across twelve files, then leave the original function untouched in a thirteenth file it apparently didn't search, with zero indication anything had been missed. It wasn't even a hard case, the file just wasn't in the directory it happened to grep first.
What was your moment? And did it actually change your workflow afterward, or did the trust creep back in after a week like it always seems to for me?

Very excited that folks responded so well to the initial Product Hunt Launch of ZeroClick. We got #9 on Wednesday without any paid marketing! We've got some exciting things to launch in the near future as well, so hopefully folks will, as they say, 'stay tuned.' ;P

Summer months bring vacations, travel, more time spent outdoors, and less time for online or work-related activities.

Because of this, it s easy to forget to check Product Hunt and lose your streak.

I was thinking about this because it sounds like such a small product decision, but I don t think it actually is.

Someone signs up with Google. Six months later they are on their iPhone and tap Sign in with Apple. Same person, different identity provider. And if they use Hide My Email, you may not even get the same email address.

So what should the product do?

Creating a new account feels wrong because now their history, billing, settings, or subscription can end up split across two profiles. But automatically linking accounts based on email also feels risky, because now you are assuming that matching email addresses are enough proof that both identities belong to the same person. And then Apple makes it even messier because the emails may not match at all.

Everyone launching for the @producthunt @OpenAI , let s try something fun:
Send to GTP-6 Astra:

1. The Product Hunt cat