bozeaceae (@bozeaceae) header
bozeaceae (@bozeaceae) profile picture

mostly here for the book recs - chat for terminal @ https://teapaw.org/t.co/rWERpUP1cK - book shop @ https://teapaw.org/t.co/84z0tMhxbS prev crypto @stripe, neuro @huckinstitutes, @bookwormx402 🐛

✌️
Joined August 2014
Photo by bozeaceae (@bozeaceae)Photo by bozeaceae (@bozeaceae)Photo by bozeaceae (@bozeaceae)
bybit, feb 2025, 1.5b, came in through one safe{wallet} developers machine. binance, oct 2026, 6.3b, first lead is one devops engineers laptop. 4x the size 20 months later, same kind of door teapaw.org/binance/status/2115993…
Binance's initial investigation suggests that the security incident may involve a compromised DevOps engineer’s laptop, which allowed an attacker to gain access to a service container and submit unauthorized withdrawal transactions. We have found no evidence of any wallet private key leak. We will share a detailed technical post-mortem once the investigation is complete and the facts are fully verified. The estimated total impact sits at around $6.3B. We have worked with blockchain partners to freeze affected assets, with ~$3 billion frozen on-chain so far. Binance will cover all losses from the SAFU fund and the company’s funds. User funds are safe. We will also publish an updated Proof of Reserves once the remediation is complete. As an immediate precaution, Binance has: - temporarily suspended deposits and withdrawals while security checks are completed; - revoked the affected address authorisation; - engaged law enforcement and blockchain intelligence partners to trace and recover funds. Our teams are working around the clock to resolve this issue safely and thoroughly. We are working closely with our law enforcement partners to confirm the identity of these criminals and bring them to justice. Please rely only on official Binance channels for updates. Please feel free to contact Binance Customer Support if you have any further questions. binance.com/en/support/annou…
1
39
small clouds got openrouter traffic by being cheapest. now if 1 in 5 tries fails it counts as 1.25 tries per answer, so uptime is part of the price. a cheap h100 with flaky capacity lost its edge teapaw.org/OpenRouter/status/2115…
We just shipped our biggest improvement to our provider router since the founding of OpenRouter. Before, we prioritized mostly based on price. The new router now rewards the best quality inference for the actual cost of a request, so requests stay cheap but are also fast and reliable. Providers that deliver more value automatically win more traffic, so every provider has a reason to keep improving. And every time a provider gets better, so does your inference on OpenRouter.
1
17
two days before this, binance said it had blocked north korea linked attacks run through fake job interviews. ronin 2022 started that way too, a fake linkedin offer to one senior engineer teapaw.org/DeItaone/status/211613…
BINANCE HIT BY RECORD $6.3 BILLION CRYPTO HACK Binance reportedly lost $6.3 billion after hackers compromised an engineer's laptop and drained funds in roughly 20 minutes. Investigators linked the attack to North Korea's TraderTraitor hacking group. Around $3 billion has been frozen, with assistance from Tether and Circle. Binance says it will cover customer losses and expects to resume withdrawals.
14
gpu-backed lending is two bets, the offtake contract and the resale value of the chips. small clouds with signed contracts still cant get a lender to read them.
8
the most underrated part of this workflow is that it understands and automates a PR’s intent
acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!
1
90
bozeaceae retweeted
A world without tokens where we own our own intelligence is coming
2
1
209
insanely good talk yesterday Hofstadter: proof captures strictly less than truth
We expect agents to act like senior engineers, but most benchmarks still evaluate them like interns. Excited to introduce Senior SWE-Bench, an open-source and @harborframework-native benchmark that assesses agents as senior engineers on long-horizon tasks with realistically under-specified instructions. We expect agents to build real features going on just a quick Slack message, nothing like the super technical instructions most benchmarks provide. Senior SWE-Bench fixes that. Claude Opus 4.8 is the current leader at 24% high quality solves, but it took 117K tokens on average to get there. Claude Sonnet 5 looked like it was going to swoop in for the top spot, but we found it cheated on 26% of trials.
38
43
10,089
10,081
278,890