Barely Technical @barelydev

The default font on Omarchy is beautiful! Makes other operating systems ugly. There are a lot of other aesthetic things about Omarchy, but the font is just too difficult to ignore. Not sure why a lot of people are not talking about it.

@Alibaba_Qwen @grok What is the minimum hardware spec needed to run this locally?

@KrishaAsiagh I have a serious question. How will they change their images in passport?

For the engineers, It is a zero shot classifier with calibration training, and the founder agreed with that framing on Hacker News. The 193x speed claim is against LLMs running full chain of thought, and its benchmark grades against the average of two other models' answers. Test it on your own data before you trust the headline number.

Most vibe coded apps have one fragile line in them. It is the prompt that says "reply with only yes or no" and then hopes the AI actually does. A model launched this week that exists only for that line. It is called Jev. It does not chat, write, or explain. You give it some text and a question with fixed answers, and it hands back a percentage for each answer plus a number for how sure it is. Is this signup spam. 91% yes. Which bucket does this expense go in. Travel 84%, meals 11%, other 5%, confidence 0.8. That "how sure" number is the part I have never had. Every check in my own app runs through a chat model, and eight calls on one identical photo once split 5 to 3 between two answers. Nothing in the reply told me it was unsure. With a confidence number you can write the one rule every app needs. If it is sure, do it. If it is not, ask a person. The price is $0.042 per million tokens in and nothing out, because it never writes anything out. One check on a page of text costs about three thousandths of a cent and comes back in a tenth of a second. It is waitlist only, it cannot see images, and it cannot invent an option you did not give it. But if your app makes small decisions all day, this is what those calls should have looked like from the start.

The agent was repairing the graphics driver. Every screenshot on that machine is produced by that same driver. So a screenshot cannot prove the driver works. The webcam does not go through the driver. Point it at a mirror and the agent gets a witness the bug cannot touch. That is the reusable part. When an agent checks its own work, the check has to come from outside the thing it changed.

Justin Schroeder @jpschroeder

3 weeks ago

Can’t make this up…the MacBook is using its webcam to look at its screen in a mirror to improve AMD Radeon chip support in Omarchy.

451 926 14K 1.2M 2K

@dhh the driver it was fixing is the same one that makes screenshots. so a screenshot could not prove the fix worked. a webcam does not use that driver. the mirror is just the last mile.

@Saboo_Shubham_ And then you have a company that literally has aislop in it's name, claims to run companies autonomously and also raised $30 million in funding! IYKYK ;)

@kimmonismus Best way to maximize utility out of existing anthropic max plan is to claude subscriptio is to use Opus 4.8 till the subscription ends and switch to Codex till Anthropic ships a better model again.

@AlexFinn @openclaw Precisely the reason why I stopped using open claw. I spent more time maintaining it.

@LewisHowes Thank you for the push that i needed very badly today!

@marclou Anyone who says "build cool shit" over need audience actually never shipped anything

@birdabo Some of us are probably the last people to experience pre internet and pre AI world It would be very difficult to explain it to someone who never experienced it.

Five of your six examples are loops, not tasks. Monitor the community, poll the accounts every 15 minutes, click through the apps, catch the moment you post. None of that needs a smarter agent. It needs one that is still awake at 3am holding the same state it had at noon. That is the part everyone else shipped as config, which is exactly where your 10,000 decisions came from.

The number worth tracking more than the model benchmark is that the HBM versus conventional DRAM wafer split at Samsung, SK Hynix and Micron. That ratio sets the floor price of the hardware you buy in 2027 and the ceiling on how many agent steps anyone can afford to run.

Everyone agreed memory is the rate limiter. Almost nobody said which memory they meant. Builders heard context windows. A week earlier, SpaceX and Tesla had committed $16.8 billion to a fab that makes its own logic and memory. Those are the same constraint seen from opposite ends. Generating a token is mostly a read, not a calculation. The model streams its weights and its accumulated context out of memory for every token it produces. An agent makes that worse on purpose. It keeps state, re-reads it every step, and takes hundreds of steps where a chat takes one. Add FLOPs to that and very little happens. The accelerator sits waiting on the memory bus. So agent memory and high bandwidth memory are not two subjects. Agent memory is the workload, HBM is the pipe, and the pipe is the scarce part. Three companies make over 95% of the world's DRAM, and every wafer they move to HBM is a wafer that never becomes the RAM in a laptop. TrendForce has conventional DRAM contract prices rising 58 to 63% this quarter. J.P. Morgan puts the full move above 400% between the start of 2024 and the end of 2026, and expects the shortage to run for years. That is what the rate limiter really is. Not a flaw in anyone's agent framework, but an allocation decision made by three suppliers that then reprices hardware for everyone standing downstream. Which is why the response taking shape is a building rather than a framework. When the bottleneck moves from compute to memory, leverage moves from whoever trains the best model to whoever decides where the wafers go. A fab is the only way out of being a customer of that decision.

Naval says people who are serious about software train their own models. It is the most expensive advice in AI right now. That is Alan Kay's advice about hardware, and hardware never lost half its value in ten weeks. Opus 4.8 scored 18.7 on Frontier-Bench in May. Opus 5 scores 43.3 now, at the same price. Anything you trained in May is behind what you can rent today. And training would not have saved my worst run anyway. Last month I ran the same coding model, same spec, same harness, on two different days. Sunday it went 12 of 12. Monday it went 0 of 12, ran for 26 minutes, billed me $0.92, and never wrote the page. Owning those weights would have changed nothing. The failure was in the run, not the model. What caught it was a pass/fail list I wrote before the run. That list is the part that compounds. It works on a model I trained, a model I rent, and whatever ships in October.

Anthropic confirmed a custom chip team today without any timeline, fab decision, spec for what the chip actually does. A serious chip program is a $500M line item. Nobody spends that to save money on hardware. The real news is the hiring brief for engineers with experience spanning hardware and software, to codesign the chips and the models together. Google is the only company that has ever closed that loop, with TPUs and Gemini. Compute is a lab's cost of goods. Every price cut shipped this year was a bet that cost per token keeps falling, and the models getting smaller was never on the table. Last week I ran 100 image generations through a product I built. $3.28. I never negotiated that number. It was settled years ago by someone choosing a memory architecture. Every app built on an API is renting margin from a chip roadmap it has no vote in.

Without a timeline, fab decision and spec this announcement is essentially a hiring brief. they are looking for engineers who span hardware and software, to codesign the chip and the model together. That's a different bet than cheaper silicon. Google is the only one who has closed that loop. And the multi chip line isn't a hedge. A lab that can move a training run across four vendors gets a better price from all four the moment building its own becomes credible.

@gregisenberg This also PARTLY explains the explosion of AI girlfriend/AI companion apps.