My boys and I continue to build our little game with AI and a side adventure has been voice overs with custom voices with Qwen3 TTS. Wrote down my learnings from playing with it for a while now. https://t.co/3wMz0jnMZK
#Tutorials / practice#Speech#Open-source ecosystem
Inspired by Divyansh Agrawal's qwenputer, Drew Breunig wrote a runnable NES 6502 CPU emulator into the weights of Qwen3.5-4B, and it can now (very slowly) run NES ROMs such as Super Mario Bros inside Qwen. In a Hacker News comment, he disclosed the prompts used when building the system with Opus 5.5, noting that Opus found and used the NES CPU consistency test suite that Christopher Pow published 15 years ago.
#English text is being prepared.#English text is being prepared.#Open-source ecosystem
#Evaluations / benchmarks#Video#Open-source ecosystem
Baseten's engineering blog states that incremental weight synchronization for the approximately 770GB GLM-5.3 checkpoint dropped from an average of about 36 seconds to 15 seconds, and request pauses fell from 6 seconds to 0.8 seconds. The new design uses the weights on the GPU as the parent copy, no longer keeps a full copy in CPU memory, and uses Adler-32 checksums to perform constant-time updates on changed bytes. The freed host memory is used for KV cache offloading; at a concurrency of 48, the cache hit rate rose from 2% to 92%, and per-GPU output throughput increased 3.2x. For Kimi K3, the 8.4GB incremental sync takes 75 seconds with a 4.1-second pause.
#Tutorials / practice#English text is being prepared.#Reasoning
Drop 2/15 Are we actually measuring the things we ultimately want our voice AI models to achieve? The best AI voices are becoming hard to tell apart. From each other. Not from humans. 🚀 Introducing Turing TTS: an evaluation that measures how often human listeners mistake AI-generated speech for real human speech. We tested leading TTS models against real human speech. Even the best model fooled listeners only ~10% of the time. With Turing TTS, we hope to contribute to a broader discussion within the research community about how we measure progress in voice AI. If one of our goals is to develop speech that is indistinguishable from human speech, how well do our current evaluation methods capture progress toward that goal? We don’t claim that Turing TTS is the right way forward, or that human indistinguishability should be the goal of every TTS system. Rather, we hope these findings encourage the community to collectively examine whether blind pairwise human evaluations of naturalness are sufficient, and what else we might need to measure. Results are now live on @voicearena_ai.
#Evaluations / benchmarks#Speech#Google
A heise reporter used ArtCraft's FilmCraft, EffectCraft and PhotoCraft to fully edit a c't 3003 video and produce a thumbnail, concluding that these still-Alpha open-source tools are already usable for real work. In testing, Premiere rendered about one-third faster with hardware encoding and twice as fast with software encoding; FilmCraft was laggier on Windows than on macOS and Linux, and EffectCraft froze the entire machine after running for a minute or two on Zorin OS. The author also used Codex to fix several bugs in his own FilmCraft branch and added a FilmCraft–EffectCraft linkage feature similar to Adobe Dynamic Link.
#Evaluations / benchmarks#Open-source ecosystem#English text is being prepared.
Using test case generation as an example, the article explains how to rewrite wishful prompts like "please help me generate test cases" into a SKILL.md that Claude Code can follow. The author provides a four-step skeleton: understand the requirements; identify four types of scenarios—normal flows and exception scenarios, boundary conditions, and permission checks; generate test cases according to fixed fields; and check against a self-review checklist. The article also explains that description should clearly state the trigger words, and when_to_use should indicate applicable and non-applicable scenarios. The comparison in the article shows that before the rewrite, AI output only three plain-text test cases; after the rewrite, it output twelve table-form test cases covering scenarios such as unauthorized access, and the author recommends running through manually written test cases to verify format and coverage.
#Tutorials / practice#Agents#English text is being prepared.
https://t.co/I431zBBUB3
#Tutorials / practice#English text is being prepared.#GitHub
Addy Osmani, a member of the Anthropic Claude Code team, wrote in a post that users generally over-prompt Claude, and suggested using a single prompt to clearly state the goal and acceptance criteria, then letting the model execute on its own, with reasoning effort starting from /effort medium. He mentioned that Claude Code once removed more than 80% of the system prompts for models such as Claude Opus 5 and Claude Fable 5, with no measurable decline in coding benchmark performance, and suggested users use /doctor prompt-audit to find prompts written for older models. The article also suggests first making a single session capable of completing tasks independently before considering parallel multi-session work, and focusing attention on verifying results.
#English text is being prepared.#Agents#English text is being prepared.
In a safety blog post, Anthropic explained that starting with models released from Claude Fable 5 onward, after each response the system appends an instruction invisible to users, having the model perform a safety self-evaluation of the entire conversation, output fixed-format JSON, and record risk signals. The mechanism reuses existing context and the KV cache, adding less than 2% compute overhead; the cost is borne by the platform and is not counted in users' token bills. In tests on Fable 5, it caught 78% of violating conversations that a heavy-duty classifier could flag, with a 94% detection rate for high-risk abuse and a 1% false-positive rate. Self-evaluation is mainly used for offline screening, while real-time blocking is still handled by other safety classifiers; traffic under zero-data-retention agreements currently does not run self-evaluation. The article also mentions that Fable 5.5 is being tested, and some users say Opus 5.5 will be routed to a new model with better performance.
#Safety / alignment#Anthropic#English text is being prepared.
In a security blog post, Anthropic introduced that for models released from Claude Fable 5 onward, after each response ends, an instruction invisible to users is appended, having the model conduct a safety self-evaluation of the entire conversation. This mechanism reuses existing context and the KV cache, adding less than 2% compute overhead; on Fable 5 it captured 78% of violating conversations that a heavy-duty classifier could flag, with a detection rate of 94% for high-risk abuse and a false positive rate of 1%. The evaluation results are not shown to users and do not enter subsequent conversations; they are mainly used for offline aggregate screening, while real-time interception remains the responsibility of other safety classifiers.
#Safety / alignment#Anthropic#English text is being prepared.
#Evaluations / benchmarks#Reasoning#Meta
#Evaluations / benchmarks#Reasoning#OpenAI
#Evaluations / benchmarks#Reasoning#Meta
#Evaluations / benchmarks#Reasoning#Open-source ecosystem
#Tutorials / practice#Reasoning#English text is being prepared.
i've gotten a lot of questions about how i manage my X account with grok bot, so i'm sharing my bot tibot today! he watches your mentions and: • finds every post about you or any keywords, tagged or not • gives one short, sorted digest a day (or hourly, your call) • skips spam and noise • translates non-English posts • can auto block trolls and abuse • never posts for you i still write all my posts and articles by hand but tibot has been very helpful with keeping me in the loop. hire tibot today! https://t.co/OaEAunGL8Y
#Product updates#Agents#English text is being prepared.
Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets The Artificial Analysis Intelligence Index is our composite measure of model capabilities across tasks reflecting real-world usage today. v5 is our biggest upgrade since v4 launched in January. With v5, 60% of the Index is now based on evaluations with private test sets or held-out answers. Alongside Intelligence Index v5, we’re launching the Artificial Analysis Progress Index v1, which tracks model capability over time on one continuous scale. New to the Intelligence Index: ➤ FrontierCode 2.0: Cognition's newly-launched private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent's change ➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment Upgraded: ➤ HLE-Diamond (replacing Humanity's Last Exam): a refined 1,000-question version of Humanity's Last Exam, split evenly between reasoning and knowledge questions ➤ AA-Omniscience v1.1: An updated dataset with saturated and public set questions removed, new questions added, and ambiguous or erroneous questions revised ➤ CritPt v2: a private, 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0 Removed from the Index: GDPval-AA v2.1, SciCode, and AA-LCR v1.1 Key results: ➤ Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50 ➤ The open weights gap widens from 3 points to 12: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32 - 26 points behind the leader and below Claude Haiku 5.5 (max, 36) ➤ Cost per task varies by more than 13x among the leading models: of the 10 highest-scoring models shown, GPT-6.1 Terra (max) is the cheapest at $0.96 per Intelligence Index task and Claude Fable 5.1 (max) the most expensive at $13.04
#Evaluations / benchmarks#Anthropic#OpenAI
#Tutorials / practice#English text is being prepared.#OpenAI
#Tutorials / practice#Agents#English text is being prepared.