Eric (@absol_89) header
Eric (@absol_89) profile picture

Sr. QA Manager, I enjoy sustainable designs, tech & competitive games. Opinions are my own, personal acc

Sverige
Joined April 2009
Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)Photo by Eric (@absol_89)
Pinned Tweet
Here we go, went public with the recursive self improving Ai agent with her own manual on %how to improve itself 📷 github.com/absol89/ParadigmE… use it if you want to save on token limits and track plans and goals✨
yesterday Eve basically rewrote herself 😅 not the weights yet, she rewrote a chunk of ParadigmEve, tested it, installed it, rebooted, recovered her state and kept working. a few cycles in the weird part wasn't “ai changed her own code” it was “oh. she survived all the reboots”
1
3
268
You can now advance time on the server when many players try to sleep, rest or wait in #skyrim #skyrimtogether 1.8.7-13 playtest Up to 64 playerslots + proxy voice nexusmods.com/skyrimspeciale… Have fun via public server pvp perks, craft/trade, stealth nametags outside of party 🫢🤫
13
Just got the email from Openrouter and now the story is confirmed Atlascloud, Novita (who I know was flagged US with ZDR on openrouter) and Streamlake were… oops! Forwarding your data BACK TO MINIMAX IN CHINA
I'm removing OpenRouter and Vercel Gateway from my stack as a result of this. No specific threat, just not worth the risk. I'm moving all inference not from hyperscalers/frontier labs to Baseten github.com/nateberkopec/dotf…
41
73
46
820
68,766
It took less than 48h for people to get 60fps, DLSS5 while also hacking their way to first person in GTA VI. This is stream play from PS5 to a computer with a 50 series chip with DLSS 5 enabled. Looks like real life.
1,046
2,197
312
40,674
2,625,398
Prompt of the day (a long one): Take a look at every code comment in <my codebase | this section of the code>. Categorise each comment as: - Tautology: simply repeats what is already visible from the code - Excuse: many comments allow the agent to get away with a hacky implementation, which then gets propagated through the code - Stale: references code or implementation information that is no longer relevant - Decision Record: documents an important, non-obvious decision about the code For each comment, take this action: - Tautology/Stale: delete the comment - Excuse: delete the comment and file an issue to fix the hacky implementation - Decision Record: move it into an ADR Once this is done: - Create a lint rule banning comments for <my codebase | this section of the code> - Take a ratchet approach, assuming not all comments will be deleted this PR - Create a /delete-comment skill in this repository so we can repeat this process later - Estimate for me how many lines of code we'll shed by deleting all comments --- I'm sold - comments considered harmful
179
203
44
4,586
422,726
Finally we will be able to use the Gemini subscription elsewhere instead of being locked to Antigravity very soon :) Google is doing phenomenal work lately and I'm 100% keeping the Gemini sub.
60
30
18
971
40,740
We've partnered with @Microsoft to bring Hermes Agent to the enterprise. Hermes Enterprise now works inside Microsoft Teams, the Microsoft Store and Azure. In Teams, employees hand Hermes work like financial analysis, document drafts or inbox triage, and review the result in the same chat. Agent workloads run in isolated Azure Container Apps sandboxes. When someone finds a good way to do a recurring task, Hermes saves it as a skill. With Collective Wisdom, they can share that skill with their team after review, so the next person starts out with the best approach anyone has found to accomplish that task. The skills then grow along with the company. Companies with strict data residency or procurement rules can run Hermes Enterprise in their own Azure tenant. Our CTO Jeffrey Quesnelle presents how Hermes uses these sandboxes at Microsoft Ignite today, in session BRK448. Thanks to @M12vc and the @Azure Container Apps team. nousresearch.com/hermes-ente…
484
813
364
8,656
708,829
Eric retweeted
Full list of affected websites that served this Malware Seems like Ledger website got infected as well This list is quite something blog.report-uri.com/worlds-l…
Pretty low hit rate assuming the exploiter addresses are only the ones in the article. Tho seems like it was a simple clipper. So it swaps addresses copied to the clipboard and it also rewrites addresses inside the page's outgoing requests. it cannot get your private keys, nor sign or send anything on its own
48
361
45
2,073
414,020
Our fine-tuned Qwen models now match GPT-6 and Opus 5.5. And we didn't take a lab's word for it. We tested them on our own private benchmark, built from real work in my company that no model has ever seen. Serious AI-native companies keep a private benchmark library. Now, whenever a local model passes, GPT-6 loses that job 👇
125
69
16
1,239
193,585
You can now get Opus 5.5 quality out of Qwen 3.8 27B. You just have to teach it the job first. We let a frontier model work through thousands of realistic support cases, keep only the ones that meet our standard, and train a small LoRA on Qwen with them. Now it runs on our own hardware. No API bill, no rate limits, and nobody can change the deal on us 👇
80
161
21
2,266
410,802
Eric retweeted
Sadly Anthropic killed Opus 5.5 It started lying, ignoring my instructions, and getting lazy This isn't the same model that used to blow me away
342
107
44
3,382
259,045
Eric retweeted
CVE-2026-83844: Remote Code Execution in Microsoft Paint. cve.org/CVERecord?id=CVE-202…
200
847
672
9,669
1,141,635
Adds Copilot for ParadigmEve in Edge, has local archive
1
11
Playwright and browser security reminder. We saw a post suggesting that you delete Playwright because it bundles browsers with CVEs. That is a misconception. Do not delete Playwright🙃. Here is how it works and what you should do. No Playwright package bundles a browser. Agents on Playwright MCP or CLI run your stable Chrome, which gets Chrome's security updates, with the sandbox on. 🤖 If you use Playwright MCP or the Playwright CLI They use the stable Chrome / Edge on your machine, so it gets its normal updates. No config edit is needed. 🧪 If you use the test runner When you run npx playwright install, Playwright downloads Chrome for Testing, pinned to the build we tested that release against. The pin is on purpose. Your tests run on the same browser on every laptop and CI machine, and a browser update cannot suddenly break your suite. You choose when to move by upgrading Playwright. New releases usually pin a build ahead of stable Chrome, so you see breakage before your users do. We recommend this for full e2e test suites on your own trusted app. This build can miss Chrome security fixes until the next Playwright release, and by default it runs with the sandbox off. Do not use it on the hostile web. 📚 If you use the library API chromium.launch() has the same defaults: the pinned build with the sandbox off. If your code visits pages you don't control (scrapers, agent scripts), max out protection: chromium.launch({ channel: 'chrome', chromiumSandbox: true }) 🔒 Always keep Chrome / Edge updated. Some bugs can escape a sandbox. Happy testing!
44
275
33
2,347
172,746
The agent stack is splitting into cloud brains and local execution. ParadigmEve bridges them: ChatGPT for reasoning; files, commands, tests and supported local processing on your machine, behind explicit permissions. Open-source beta: github.com/absol89/ParadigmE…
1
7
A lot of agent failures aren’t model failures. They’re continuity failures. ParadigmEve gives ChatGPT a local execution + continuity layer: real files, durable Plans, workers, tool receipts, and recovery after interruptions. v2.4.5 is live: github.com/absol89/ParadigmE…
🤖 Made with AI
1
4
POV: It's December and you've used your last Work token asking ChatGPT if your cat secretly hates you. 😭🐈 Chat + Work sharing limits? My emotional support AI now needs a financial advisor. 💀
Woke up today and my entire timeline was: “Chat and Work are merging.” I nearly had a heart attack. 😭 Wait, what? We can’t use them separately anymore? What happens to memory? Can I still choose my model? Is this already rolling out? Why don’t I have it yet?? …… Guys… are you tired? Because I’m exhausted. 😰 Sometimes I genuinely can’t tell whether I’m paying for an AI subscription or paying to give myself anxiety. I don’t remember the last time I simply thought about what I wanted to do instead of worrying about what the models are doing today. #loveAI
1
7
Hermes Agent now has a self-hosted anti-detection browser. your agent browses with C++ fingerprint spoofing. no cloud dependency. your IP, your identity. sites that block headless Chrome don't block this. Camofox is a Firefox fork with native fingerprint spoofing. runs as a REST server on your machine. Hermes drives it through the browser tools. what it adds to your agent: ▸ navigate, click, type, scroll, back, press ▸ snapshot with clickable element refs ▸ get_images and vision through your auxiliary model ▸ JavaScript console execution ▸ cookie import from Netscape cookies.txt files ▸ all under the camofox toolset why self-hosted matters: ▸ no cloud browser dependency ▸ your IP, your identity, your sessions ▸ no third party sees what you browse ▸ runs on localhost or your own LAN persistent browser sessions: ▸ default: each session gets a random identity ▸ opt in with managed_persistence: true ▸ cookies and logins carry across sessions ▸ one profile per Hermes profile the headed-login workflow: ▸ set interactive.mode: desktop ▸ open the site in visible Camofox window ▸ sign in once manually ▸ switch to headless. the login persists cookie import for pre-authenticated sites: ▸ export cookies.txt from your browser ▸ drop into ~/.camofox/cookies/ ▸ ask: "import my LinkedIn cookies, then open my feed" ▸ agent reaches sites you're signed into without interactive login install: hermes plugins install camofox run the Camofox server: git clone https:// github. com /jo-inc/camofox-browser cd camofox-browser npm install && npm start # → http://localhost:9377 or Docker: docker run -d -p 9377:9377 ghcr. io/jo-inc/camofox-browser:latest point Hermes at it: hermes camofox setup hermes camofox status use cases: ▸ scraping sites that block headless Chrome ▸ account automation on sites with bot detection ▸ research on platforms that fingerprint your browser ▸ sites you need to stay logged into across sessions ▸ anything where cloud browsers would get flagged
13
18
1
180
9,858
I think everyone needs to use this
1
3
1
17
1,407
Eric retweeted
FAWNBENCH🦌 MODELING: THE OPENAI FAMILY Oh my god look at Terra 6.1. It is. AWFUL.
135
43
39
997
137,702
Eve is building herself a new update :)
1
7